Paper Citation Record · LEDGER

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

As of 6 August 2026, this Paper Citation Record lists 100 of 300 outbound references and 17 inbound Pith citation observations for arXiv:2502.05206.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.05206 v6

Coverage vector

measured 100 of 300 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-23T04:39:04.591722Z

measured 117 of 117 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:40:54.492314Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

100 of 300 outbound references displayed

verified exact35
verified fuzzy65
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d4507708-96c6-405d-b57d-b85d947e2ad8 · outbound

This paper cites Patch-fool: Are vision transformers always robust against adversarial perturbations?.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Patch-fool: Are vision transformers always robust against adversarial perturbations?

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.927020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 520edf65-12a4-4c5f-a890-b9db88c80a27 · outbound

This paper cites Slowformer: Adversarial attack on compute and energy consumption of efficient vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Slowformer: Adversarial attack on compute and energy consumption of efficient vision transformers

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.824536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eb6ef798-b396-4f58-bc4c-c72011429c63 · outbound

This paper cites Pe-attack: On the universal positional embedding vulnerability in transformer-based models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Pe-attack: On the universal positional embedding vulnerability in transformer-based models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.882161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 39dde15e-c81d-47a2-b9cb-d6db8dc473f3 · outbound

This paper cites Give me your attention: Dot-product attention considered harmful for adversarial patch robustness.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Give me your attention: Dot-product attention considered harmful for adversarial patch robustness

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.923127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e6a4a8d9-1c49-4d99-b3cc-c1f8c413f25c · outbound

This paper cites Towards understanding and improving adversarial robustness of vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Towards understanding and improving adversarial robustness of vision transformers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.031516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fae9c966-f986-460c-8225-d4220815d472 · outbound

This paper cites On Improving Adversarial Transferability of Vision Transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety On Improving Adversarial Transferability of Vision Transformers

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.885322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2f979305-19f3-4d7c-8a93-5f0d629cd1a5 · outbound

This paper cites Gen- erating transferable adversarial examples against vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Gen- erating transferable adversarial examples against vision transformers

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.919209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ccf3cef1-523d-4816-ad14-e4a6028c5f8d · outbound

This paper cites Towards transferable adversarial attacks on vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Towards transferable adversarial attacks on vision transformers

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.108036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 301cc788-709b-4ebe-b3d5-ebeff795b37f · outbound

This paper cites Boosting adversarial transferability with learnable patch-wise masks.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Boosting adversarial transferability with learnable patch-wise masks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.112069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 726cf37a-47a2-4856-9b87-d811e9e91186 · outbound

This paper cites Transferable adversarial attack for both vision transformers and convolutional networks via momentum integrated gradients.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Transferable adversarial attack for both vision transformers and convolutional networks via momentum integrated gradients

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.894588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d1114d34-4e54-498a-8a07-253f11119e1e · outbound

This paper cites Transferable adversarial attacks on vision transformers with token gradient regularization.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Transferable adversarial attacks on vision transformers with token gradient regularization

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.898378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bd27b953-773c-4719-94c0-e442b0ed1fc8 · outbound

This paper cites Improving the adversarial transferability of vision transformers with virtual dense connection.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improving the adversarial transferability of vision transformers with virtual dense connection

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.915073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cc10c1a2-ccc4-477c-b5f5-8f93b63be8bf · outbound

This paper cites Attacking transformers with feature diversity adversarial perturbation.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Attacking transformers with feature diversity adversarial perturbation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.837109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation becbbdd4-a535-46e5-93ba-d1109769bd73 · outbound

This paper cites Decision-based black-box attack against vision transformers via patch-wise adversarial removal.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Decision-based black-box attack against vision transformers via patch-wise adversarial removal

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.127613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 13b67fa4-f705-436e-8e23-3974300441bb · outbound

This paper cites Improving transferable targeted adversarial attacks with model self-enhancement.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improving transferable targeted adversarial attacks with model self-enhancement

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.020025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4b59fed6-bc34-4d26-b6c7-369573f0b7a6 · outbound

This paper cites Improving transferability of adversarial samples via critical region-oriented feature-level attack.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improving transferability of adversarial samples via critical region-oriented feature-level attack

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.886364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 73ab4dad-19f4-4fe1-ae57-b65ce304f7b8 · outbound

This paper cites Adversarial Token Attacks on Vision Transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Adversarial Token Attacks on Vision Transformers

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.722137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7dcca432-441f-473c-9b7a-596242ba7912 · outbound

This paper cites Understanding and improving adversarial transferability of vision transformers and convolutional neural networks.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Understanding and improving adversarial transferability of vision transformers and convolutional neural networks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.890411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d88331f1-59df-4f85-9575-c0ff762baa54 · outbound

This paper cites Towards transferable adversarial attacks on image and video transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Towards transferable adversarial attacks on image and video transformers

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.902237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ea35ba4e-4a3a-4272-b446-ab9feb184b35 · outbound

This paper cites Towards efficient adversarial training on vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Towards efficient adversarial training on vision transformers

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.056779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6581608f-eac7-4d3f-8b15-0024fc90be82 · outbound

This paper cites Patch vestiges in the adversarial examples against vision trans- former can be leveraged for adversarial detection.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Patch vestiges in the adversarial examples against vision trans- former can be leveraged for adversarial detection

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.987228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6cf929a3-114d-4d76-b740-6e227591806f · outbound

This paper cites ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformer.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformer

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.979913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 142bffe4-2a5c-40f7-9b09-7cad61c6711d · outbound

This paper cites Understanding and defending patched-based adversarial attacks for vision transformer.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Understanding and defending patched-based adversarial attacks for vision transformer

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.860994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ae60aadd-0218-4a26-90e1-a97d56c02be6 · outbound

This paper cites Diffusion models demand contrastive guidance for adversarial purifi- cation to advance.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Diffusion models demand contrastive guidance for adversarial purifi- cation to advance

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.868779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2853f39e-a7c6-4839-99a7-7a25542ef225 · outbound

This paper cites ADBM: Adversarial diffusion bridge model for reliable adversarial purification.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety ADBM: Adversarial diffusion bridge model for reliable adversarial purification

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.913047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 180603a0-5868-47d5-a98f-38c76231c091 · outbound

This paper cites Instant Adversarial Purification with Adversarial Consistency Distillation.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Instant Adversarial Purification with Adversarial Consistency Distillation

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.710245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6d84dc1a-988e-4371-98c2-c630c8e62767 · outbound

This paper cites Are vision transformers robust to patch perturbations?.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Are vision transformers robust to patch perturbations?

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.048444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2c5ec92d-c60e-4f21-9caf-7446b705040d · outbound

This paper cites When adversarial train- ing meets vision transformers: Recipes from training to architecture.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety When adversarial train- ing meets vision transformers: Recipes from training to architecture

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.853195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4a0cd5f7-e3c8-4ef5-9d2f-0d041b8e4eef · outbound

This paper cites Robustifying token attention for vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Robustifying token attention for vision transformers

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.801002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 90807744-c570-4a09-87c6-1a8d864619bc · outbound

This paper cites Improving robustness of vision transformers by reducing sensitivity to patch corruptions.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improving robustness of vision transformers by reducing sensitivity to patch corruptions

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.804999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 97da5ab8-8cd8-46ca-a533-0a4389e06095 · outbound

This paper cites Improving interpretation faithfulness for vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improving interpretation faithfulness for vision transformers

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.797167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 77867cea-1c09-4ff3-997b-d5ef2b27d0b9 · outbound

This paper cites Random entangled tokens for adversarially robust vision transformer.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Random entangled tokens for adversarially robust vision transformer

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.808884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 12fbf677-6896-4abc-8046-c802189b7f50 · outbound

This paper cites Diffusion models for adversarial purification.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Diffusion models for adversarial purification

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.003374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 308d1b9c-f1d1-474e-8dc4-9b57e7ded1ba · outbound

This paper cites Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.795622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ad67eb2c-2613-4667-a8a9-d22ab9f5f633 · outbound

This paper cites Diffilter: Defending against adversarial perturbations with diffusion filter.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Diffilter: Defending against adversarial perturbations with diffusion filter

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.906013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 72b44325-da1f-4eaa-bdaa-c7c5c3976e93 · outbound

This paper cites Mimicdiffusion: Purifying ad- versarial perturbation via mimicking clean diffusion model.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Mimicdiffusion: Purifying ad- versarial perturbation via mimicking clean diffusion model

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.946245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 02e283f3-021c-4eab-a1f4-f2ce5979696a · outbound

This paper cites Lightpure: Realtime adversarial image purification for mobile devices using diffusion models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Lightpure: Realtime adversarial image purification for mobile devices using diffusion models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.938501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c88015e2-fefb-4809-b372-bd7ad1abc4f1 · outbound

This paper cites LoRID: Low-Rank Iterative Diffusion for Adversarial Purification.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety LoRID: Low-Rank Iterative Diffusion for Adversarial Purification

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.235562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9b32e6f9-9ac3-47f4-b75d-bb854234d58c · outbound

This paper cites You are catching my attention: Are vision transformers bad learners under backdoor attacks?.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety You are catching my attention: Are vision transformers bad learners under backdoor attacks?

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.962693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8c5f2521-9f6d-42bb-9285-9661be191860 · outbound

This paper cites Trojvit: Trojan insertion in vision transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Trojvit: Trojan insertion in vision transformers

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:37.011711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7d2465d3-c2ab-4db0-b6c7-d78e85190967 · outbound

This paper cites Not all prompts are secure: A switchable backdoor attack against pre-trained vision transfomers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Not all prompts are secure: A switchable backdoor attack against pre-trained vision transfomers

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.600430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c72bb732-7160-41e5-8d00-f545fba87ee5 · outbound

This paper cites Dbia: Data-free backdoor attack against transformer networks.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Dbia: Data-free backdoor attack against transformer networks

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.786222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 34018dd0-5cda-43e2-a8f0-f047aff6dbf1 · outbound

This paper cites Multi-trigger backdoor attacks: More triggers, more threats.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Multi-trigger backdoor attacks: More triggers, more threats

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.736542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 70125927-72e7-49bb-ad75-432370cfea6e · outbound

This paper cites Defending backdoor attacks on vision transformer via patch processing.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Defending backdoor attacks on vision transformer via patch processing

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.575601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7d852ece-0777-4c67-bbef-a5c27585152c · outbound

This paper cites A closer look at robustness of vision transformers to backdoor attacks.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety A closer look at robustness of vision transformers to backdoor attacks

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.742267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1019570f-b8f7-4dc6-a8f8-f8d7bd0056d8 · outbound

This paper cites Backdoor Attacks on Vision Transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Backdoor Attacks on Vision Transformers

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.214275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f52856f-4bf4-47f7-b1d9-35269606d040 · outbound

This paper cites Practical region-level attack against segment anything models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Practical region-level attack against segment anything models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.619204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ad2203df-0473-4ccd-9508-10f7122e5a00 · outbound

This paper cites Segment (almost) nothing: Prompt-agnostic adversarial attacks on segmentation models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Segment (almost) nothing: Prompt-agnostic adversarial attacks on segmentation models

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.766094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 83c1d89b-3bb1-4cfc-ac20-f16c94044042 · outbound

This paper cites Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.203936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 27211bfb-5184-412f-9270-caf38abf3e33 · outbound

This paper cites Black-box Targeted Adversarial Attack on Segment Anything (SAM).

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Black-box Targeted Adversarial Attack on Segment Anything (SAM)

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.208812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c3249f74-4000-427c-845e-af7298d9fde5 · outbound

This paper cites Unsegment anything by simulating deformation.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Unsegment anything by simulating deformation

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.675454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6e823951-1fb9-4ef2-bb5c-34762c19d735 · outbound

This paper cites Transferable adversarial attacks on sam and its downstream models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Transferable adversarial attacks on sam and its downstream models

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.734175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a6e016ba-73d0-45c5-b9cf-9b179c2fe779 · outbound

This paper cites SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.692011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c1db7297-67a1-446c-bee6-6107c108291b · outbound

This paper cites Darksam: Fooling segment anything model to segment nothing.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Darksam: Fooling segment anything model to segment nothing

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.790167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 29c03919-6963-46a5-9491-04604a372c58 · outbound

This paper cites Asam: Boosting segment anything model with adversarial tuning.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Asam: Boosting segment anything model with adversarial tuning

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.670715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1028a23f-7d75-42b5-ac4d-8980faf344d8 · outbound

This paper cites Badsam: Exploring security vulnerabilities of sam via backdoor attacks (student abstract).

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Badsam: Exploring security vulnerabilities of sam via backdoor attacks (student abstract)

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.774541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 04facf76-b7df-4386-abfc-8bf6730e523d · outbound

This paper cites Unseg: One universal unlearnable example generator is enough against all image segmentation.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Unseg: One universal unlearnable example generator is enough against all image segmentation

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.634440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c5253791-c580-45ba-93f1-af549cdfd730 · outbound

This paper cites Bad charac- ters: Imperceptible nlp attacks.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Bad charac- ters: Imperceptible nlp attacks

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.638742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5fbbbd6e-935a-49f3-8524-41d4d50ff13e · outbound

This paper cites Is bert really robust? a strong baseline for natural language attack on text classification and entailment.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Is bert really robust? a strong baseline for natural language attack on text classification and entailment

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.604053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7298d2e4-0615-4bf3-969a-bc44305674e0 · outbound

This paper cites Bert-attack: Adversarial attack against bert using bert.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Bert-attack: Adversarial attack against bert using bert

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.665483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4de37ab6-17d9-48ad-9af0-b9865c55cf0b · outbound

This paper cites Gradient-based adversarial attacks against text transformers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Gradient-based adversarial attacks against text transformers

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.661555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d8f5561d-36d0-4787-918f-2fb7a0b6aba3 · outbound

This paper cites Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.673333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 264f9fed-159d-4c25-bdca-0a37e30d6cd2 · outbound

This paper cites Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.666757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6a1afedf-6336-486d-b07a-290d06db1d82 · outbound

This paper cites Expanding scope: Adapting english adver- sarial attacks to chinese.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Expanding scope: Adapting english adver- sarial attacks to chinese

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.596331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dad0650b-7048-41e5-996a-4eeb76b8ba21 · outbound

This paper cites Adversarial Demonstration Attacks on Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Adversarial Demonstration Attacks on Large Language Models

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.806868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 43fd6788-e2b0-4b25-9ae8-de2393893515 · outbound

This paper cites Adversarial attacks on large language model-based system and mitigating strategies: A case study on chatgpt.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Adversarial attacks on large language model-based system and mitigating strategies: A case study on chatgpt

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.770418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 470eb8b6-1fc3-4b32-a927-8b06b9935c2f · outbound

This paper cites Adversarial Attacks on Tables with Entity Swap.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Adversarial Attacks on Tables with Entity Swap

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.112486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation be32f9b8-7f3c-4b43-9f23-2918c1c180df · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-05-23T04:42:34.123161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9828062f-5849-40d1-9b97-d663117bbc92 · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Certifying LLM Safety against Adversarial Prompting

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.899921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f2f8f0b8-6462-4d0c-8fbf-b2ab324969d4 · outbound

This paper cites Improving alignment and robustness with circuit breakers.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improving alignment and robustness with circuit breakers

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.778492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cf8f6f74-559e-4617-84e6-80d803ea746a · outbound

This paper cites Low-resource languages jailbreak gpt-4.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Low-resource languages jailbreak gpt-4

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.626600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f6012ba0-abe9-46d9-86b0-fa47570d8577 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.940336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3986d0c6-98fe-47c4-b65a-14f14aa4846d · outbound

This paper cites Jailbroken: How does llm safety training fail?.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Jailbroken: How does llm safety training fail?

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.686403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c3729edd-1c79-4184-be53-7383deb459f7 · outbound

This paper cites A Cross-Language Investigation into Jailbreak Attacks in Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.134448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5f881974-725b-4550-bdc6-efdfc2777273 · outbound

This paper cites EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.872115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1b9d4862-3607-430b-8c9c-ef8c5ce9d4c1 · outbound

This paper cites Is the System Message Really Important to Jailbreaks in Large Language Models?.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Is the System Message Really Important to Jailbreaks in Large Language Models?

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.075439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1ca4ac1c-1032-43a9-b2bc-e72e711de775 · outbound

This paper cites Tastle: Distract large language models for automatic jailbreak attack.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Tastle: Distract large language models for automatic jailbreak attack

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.750192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 113ace04-a48e-4fad-a159-4ca3777a66bf · outbound

This paper cites StructuralSleight: Automated Jailbreak Attacks on Large Language Models Utilizing Uncommon Text-Organization Structures.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety StructuralSleight: Automated Jailbreak Attacks on Large Language Models Utilizing Uncommon Text-Organization Structures

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.784653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ad69d10-7201-426b-9e20-a90fa9ecd089 · outbound

This paper cites CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.818659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0c47b453-4a50-4cd8-8711-f643dd53aae5 · outbound

This paper cites Play guessing game with llm: Indirect jailbreak attack with implicit clues.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Play guessing game with llm: Indirect jailbreak attack with implicit clues

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.681554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 69d41336-2ebf-48a2-b3d2-140f0afb3213 · outbound

This paper cites Evaluating implicit bias in large language models by attacking from a psychometric perspective.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Evaluating implicit bias in large language models by attacking from a psychometric perspective

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.630730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 62e381a7-d7ac-4001-a4b1-173b4eacfd10 · outbound

This paper cites LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.756304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 02bdfea2-0dc5-461c-9bd9-b4e0094b635e · outbound

This paper cites AutoDAN: Generating stealthy jailbreak prompts on aligned large language models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety AutoDAN: Generating stealthy jailbreak prompts on aligned large language models

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.558044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2d131d2d-11d1-4533-8557-0568fc07297a · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-05-23T04:42:33.679810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d8220671-ca82-4cfe-b808-b9a81b0daf04 · outbound

This paper cites Jailbreaking black box large language models in twenty queries.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Jailbreaking black box large language models in twenty queries

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.607657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e29f3c5-de65-483f-8fc0-4aa636244851 · outbound

This paper cites Masterkey: Automated jailbreaking of large language model chatbots.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Masterkey: Automated jailbreaking of large language model chatbots

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.793567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7758fee1-dae0-4588-b025-05dce8dcbdc1 · outbound

This paper cites Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.848607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0d01b685-0547-402a-a42f-38253a463a4e · outbound

This paper cites Fuzzllm: A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Fuzzllm: A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.588494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation de14a188-2096-47d3-87a3-2cdde5186f6f · outbound

This paper cites EnJa: Ensemble Jailbreak on Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety EnJa: Ensemble Jailbreak on Large Language Models

Reference 89

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.654548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d0a42fa9-2b95-42ce-9192-f70388557978 · outbound

This paper cites Red teaming language models with language models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Red teaming language models with language models

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.762034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4cd70880-6e40-44d1-bfd1-ca1d1a0e7b3b · outbound

This paper cites Curiosity-driven red-teaming for large language models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Curiosity-driven red-teaming for large language models

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.592261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 06d73ad8-a097-42db-8943-c37bc1038f72 · outbound

This paper cites “do anything now.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety “do anything now

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.646507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 637f526e-2929-40eb-97d3-90a660c36cc2 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-05-23T04:42:33.773359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9fb65307-e2e1-4b9c-a6f2-7a32e13f3fd1 · outbound

This paper cites Improved Techniques for Optimization-Based Jailbreaking on Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.240968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e4b8cf3c-3f16-45c0-87ec-e1b111785471 · outbound

This paper cites Semantic-guided prompt organization for universal goal hijacking against llms.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Semantic-guided prompt organization for universal goal hijacking against llms

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T05:17:36.738226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 23119037-8784-4bda-8a5d-ad01d32a4e2b · outbound

This paper cites Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Reference 96

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.262850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e17858c5-6305-4ec4-a4cc-c9d78526c34f · outbound

This paper cites Weak-to-Strong Jailbreaking on Large Language Models.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Weak-to-Strong Jailbreaking on Large Language Models

Reference 97

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.219547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6a3a682e-b897-4adf-9041-a885df213db2 · outbound

This paper cites An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer

Reference 98

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.224637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 835096e9-28fb-48b8-a2f6-0b9a7610125a · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 99

Resolution: verified exact; local_arxiv, observed 2026-05-23T04:42:34.192432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 40fb8e02-5ed2-48e4-9805-054843b93c9b · outbound

This paper cites Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation.

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:34.279284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation a88c5551-98a4-4c24-b971-93768a44514f · inbound

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion cites this paper.

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-23T00:15:14.797246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0f509cda-c255-45c7-ad82-639178851d27 · inbound

LeakyCLIP: Extracting Training Data from CLIP cites this paper.

LeakyCLIP: Extracting Training Data from CLIP Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-22T12:34:52.554632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 064f7a99-bcc6-4ccd-accf-47c09ccd9273 · inbound

First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge cites this paper.

First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T14:40:54.492314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc2339d5-1e8b-48fe-ae58-4daa37c4103b · inbound

CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention cites this paper.

CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T12:54:06.598065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ffed6f-5fbb-4ad7-8050-7223a99206af · inbound

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models cites this paper.

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-18T12:36:22.453973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4df0021-86ef-4500-853e-5dd7f912b2a7 · inbound

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs cites this paper.

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-21T19:00:30.400373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bbe6cccd-ecce-4f2b-98ea-1e28c4c6c256 · inbound

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP cites this paper.

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T07:47:37.549997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96e65a4e-3154-4a17-b6ba-60c5684323a3 · inbound

Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety cites this paper.

Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-15T13:17:48.274611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7cf2544-2fd7-42af-9145-150099a6cda0 · inbound

Safety, Security, and Cognitive Risks in World Models cites this paper.

Safety, Security, and Cognitive Risks in World Models Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-13T22:38:22.213669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0f400c2a-a08a-4fc5-a8db-3c4eaee9c586 · inbound

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety cites this paper.

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 166

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:06.495963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 906504e4-fbcd-4894-8862-6a55df8dd875 · inbound

SoK: Robustness in Large Language Models against Jailbreak Attacks cites this paper.

SoK: Robustness in Large Language Models against Jailbreak Attacks Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:01:08.749386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c1eafb32-4e8a-4616-bc67-c910bcde6c26 · inbound

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents cites this paper.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.823188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dd7d664a-711f-43fc-aacf-7626cedbd054 · inbound

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models cites this paper.

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:38:04.871760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2edc4021-17ee-4890-a02f-9b799d9a19f0 · inbound

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security cites this paper.

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 87

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:45:01.626483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bbfd3ba3-ea69-4d14-8767-40dca7add7ad · inbound

MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems cites this paper.

MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T00:14:04.403606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e79b7baa-e666-4a92-810d-08a3b585a0c6 · inbound

BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks cites this paper.

BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 92

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T22:36:17.840636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ca918491-74ac-4d57-8dff-e52206643b57 · inbound

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows cites this paper.

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:19.432277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.