Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation | Paper Citation Record

Observation b3d67068-1cc3-4e6f-8be0-7b572fade415 · outbound

This paper cites Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.199445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fe71ad6-57ad-4266-8612-7fd0530e0210 · outbound

This paper cites I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.253466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 627938d6-e79e-4b04-9299-f5e9e42df1d5 · outbound

This paper cites Applying sparse autoencoders to unlearn knowledge in language models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Applying sparse autoencoders to unlearn knowledge in language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.321750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5b5438-d810-47fa-81f3-99b1a64fb6ed · outbound

This paper cites Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.388754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77d84fa0-46e6-4bbc-826a-a011a1d5b69e · outbound

This paper cites Steering Language Model Refusal with Sparse Autoencoders.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Steering Language Model Refusal with Sparse Autoencoders

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.454509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba2f3f4b-2430-4bbd-8a35-ef1c2fac1daa · outbound

This paper cites Scaling monosemanticity: Extracting interpretable features from large language models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Scaling monosemanticity: Extracting interpretable features from large language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.552312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f76d637-2727-4dd4-bf88-41c468e1229b · outbound

This paper cites Understanding the decisions of large models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Understanding the decisions of large models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.616113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6265bbc8-9c57-46f2-b42d-6d9d0eb65852 · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.703450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e984a50b-2dfc-4d54-ab0a-fa2c943e4b45 · outbound

This paper cites SPML: A DSL for Defending Language Models Against Prompt Attacks.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation SPML: A DSL for Defending Language Models Against Prompt Attacks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.765489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0f91128-20e3-4d51-bd0c-f1da26be06c8 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.837394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ae6274f-493e-4d41-9408-b6a083ff8ea8 · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:31.913269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c9886d1-7f7c-423b-8d0b-5e05f6d5512c · outbound

This paper cites Adversarial Examples Are Not Bugs, They Are Features.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Adversarial Examples Are Not Bugs, They Are Features

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.006974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d688554-cd12-48cc-a878-7d4c7e750fad · outbound

This paper cites an unresolved cited work.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.096752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bc2f18e-501a-4833-a2ea-6835864e9231 · outbound

This paper cites Ddsa: A defense against adversarial attacks using deep denoising sparse autoencoder.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Ddsa: A defense against adversarial attacks using deep denoising sparse autoencoder

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.154418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca38d9a1-9a9d-45f8-bcfc-7b880faf321e · outbound

This paper cites Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.239962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a646562-beb4-455b-9b45-1a18b333f3f8 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.324026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f6c8a8-3d64-4da7-8f0d-c9205117bdcc · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Scaling and evaluating sparse autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.382109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b910cfd2-824c-4ba5-8039-15b0bb4b80b4 · outbound

This paper cites Route Sparse Autoencoder to Interpret Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Route Sparse Autoencoder to Interpret Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.471158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71db0da8-18ab-4522-966b-281e91d32b94 · outbound

This paper cites Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.540179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dbafd58-6fab-4d99-bc2e-9860eb474bd6 · outbound

This paper cites Sparsegan: Sparse generative adversarial network for text generation.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Sparsegan: Sparse generative adversarial network for text generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.604718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e25aa254-2579-4ce9-9ad3-283b9ebb2b99 · outbound

This paper cites Real-time segmentation of on-line handwritten arabic script.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Real-time segmentation of on-line handwritten arabic script

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.667105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a7542f-c27b-409c-94ed-94f66272b653 · outbound

This paper cites Fast classification of handwritten on-line arabic characters.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Fast classification of handwritten on-line arabic characters

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.758980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf25f153-f647-4869-9713-2dd73cdb6e1b · outbound

This paper cites Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.841903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c41a788d-39bb-4780-83d5-16f11f3d3ec6 · outbound

This paper cites Boosting Jailbreak Attack with Momentum.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Boosting Jailbreak Attack with Momentum

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.922403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a2da513-690e-4b56-99c0-748ef52c5472 · outbound

This paper cites Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:32.991210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abd52154-d50a-4659-b063-cc2bbd32eb46 · outbound

This paper cites Attacking Large Language Models with Projected Gradient Descent.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Attacking Large Language Models with Projected Gradient Descent

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.071055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98bbb770-7390-4731-8445-b13309036222 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.151173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c46d0d5a-1d65-40fa-b1f0-f571846445f8 · outbound

This paper cites Hijacking Large Language Models via Adversarial In-Context Learning.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Hijacking Large Language Models via Adversarial In-Context Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.221051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8da5bc0-1678-4e7d-a684-7202620ad8c0 · outbound

This paper cites PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.306997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc76b078-c515-4956-b91d-b93bed59d299 · outbound

This paper cites ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.378159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb2ddbd0-6ab7-48b3-8a03-042e64e1955d · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.469643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db1489f2-1e86-47c7-baba-c5cc027fd0c3 · outbound

This paper cites Improved Generation of Adversarial Examples Against Safety-aligned LLMs.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Improved Generation of Adversarial Examples Against Safety-aligned LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.554453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd0431ae-c85a-46f5-878f-6dcce83602e6 · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Weak-to-Strong Jailbreaking on Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.631918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2861fd44-e50f-4d4a-8c03-1ae8259f8c1b · outbound

This paper cites Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.736025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17b10907-dc4b-451b-b535-e0841e28f91e · outbound

This paper cites Don't Say No: Jailbreaking LLM by Suppressing Refusal.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Don't Say No: Jailbreaking LLM by Suppressing Refusal

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.756873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36244384-4873-47b0-b7d7-bad4ca7beacb · outbound

This paper cites Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.814112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7a5a669-88f3-429a-8668-8c7d187bf6ea · outbound

This paper cites Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.859800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 512e92fe-7ea0-4a83-b1d9-7f13210766df · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:33.972622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395708b6-947e-43d8-b952-e562b4ba357a · outbound

This paper cites Fast Adversarial Attacks on Language Models In One GPU Minute.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Fast Adversarial Attacks on Language Models In One GPU Minute

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:34.060079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5593cdcc-082e-4ea9-a8d5-680a15548693 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:34.192244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c2c932-e692-4384-ad68-e40230d919db · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:34.960696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba196737-b187-4781-964d-195ff8a829bd · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:36.139445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42d9129f-7bb4-4215-ae7b-53ab8a841f8e · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:36.299965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2fffb31-5954-4016-ac38-f43310662a1b · outbound

This paper cites Removing RLHF Protections in GPT-4 via Fine-Tuning.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Removing RLHF Protections in GPT-4 via Fine-Tuning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:36.407857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eec2fb5a-a4f3-44fc-835b-60ebb1957c71 · outbound

This paper cites Learning diverse attacks on large language models for robust red-teaming and safety tuning.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Learning diverse attacks on large language models for robust red-teaming and safety tuning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:36.553261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d72aad72-62ff-46d8-b916-81bc4d105fe5 · outbound

This paper cites Exploiting Novel GPT-4 APIs.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Exploiting Novel GPT-4 APIs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:36.707987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ff7773a-6323-4b3c-bce2-1b0df8d3a687 · outbound

This paper cites Steering Language Models With Activation Engineering.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Steering Language Models With Activation Engineering

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:36.921320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 180e7a9a-bfa9-40af-a697-a47145e9befa · outbound

This paper cites Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.044270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25011324-4e75-4273-8cdd-0c3901a57082 · outbound

This paper cites Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.155433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 725280ed-c100-4917-8f79-e5c55895d556 · outbound

This paper cites LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.285221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98dbcbb2-387b-49ad-99aa-53fe56fca48d · outbound

This paper cites Prompts have evil twins.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Prompts have evil twins

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.394563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cd7a346-7dde-45fc-bf34-b6b32029aa32 · outbound

This paper cites PAL: Proxy-Guided Black-Box Attack on Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation PAL: Proxy-Guided Black-Box Attack on Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.579293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 662af245-6dca-4328-98e9-2e7229c2d120 · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.738668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50128bf5-2104-432c-8ff7-0d38647da5fd · outbound

This paper cites Uncovering Safety Risks of Large Language Models through Concept Activation Vector.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.875871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2f845f7-2d66-4cbd-ab40-9e84ce9c8173 · outbound

This paper cites $\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation $\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.935832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd092592-9b9a-45b2-b9c7-b628184385d1 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Low-Resource Languages Jailbreak GPT-4

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.034933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cee7763d-f474-4e9d-a874-767b13499608 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Multilingual Jailbreak Challenges in Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.142157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 700de88b-473c-478c-af8f-f9dd1003bb73 · outbound

This paper cites Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.266606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94077c99-5a47-4e5b-b033-1f4b3e82c09f · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.472071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33cb0b08-c7f5-4146-80e5-df085cd44bc1 · outbound

This paper cites Does Refusal Training in LLMs Generalize to the Past Tense?.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.588823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8a82589-fba1-4a2d-a4f7-8ccec9762110 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.691439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5338dce9-2623-4bc2-bb50-8d8089c4cec1 · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.748228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cb88860-73dd-47a7-a440-dae0fdc7137d · outbound

This paper cites Distract Large Language Models for Automatic Jailbreak Attack.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Distract Large Language Models for Automatic Jailbreak Attack

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.816400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 988661c8-3b8b-4dae-b34b-8ba76988e131 · outbound

This paper cites GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:38.916981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d301f50f-4848-491b-b0b0-448c66818f48 · outbound

This paper cites Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.012270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db9352be-3e94-4c12-a714-e05670708b7b · outbound

This paper cites Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.106420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6572016-2ca6-486f-b7cd-6ddbf51ce786 · outbound

This paper cites Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.185931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9832347-69c1-485d-b07d-92509c29f29d · outbound

This paper cites Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.270858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbadbbac-3e64-4778-90c7-60019d30923c · outbound

This paper cites Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.383251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc25817-9bbc-4f3c-9f6c-b6894256d338 · outbound

This paper cites Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.494024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1cd6c39-faad-47d4-9419-a2595bb633ec · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.578072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a546f1b-868d-443b-9131-adc1338483e6 · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.676177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 994455b5-e1c7-40d3-a964-8916c933abce · outbound

This paper cites Jailbreaking proprietary large language models using word substitution cipher.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Jailbreaking proprietary large language models using word substitution cipher

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.753248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3394ec4-0e10-4687-bc61-bf5b581bd413 · outbound

This paper cites Endless Jailbreaks with Bijection Learning.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Endless Jailbreaks with Bijection Learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.837061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78b3b375-eb49-4fd2-8927-49c564fdca30 · outbound

This paper cites ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:39.978896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa6d8ef1-779b-4e8f-956b-f105db6f570c · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.072419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21da2a50-cc45-46b1-bf0a-ac8480d8d34d · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.174290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b717d4d-1dc1-44c4-9960-8658c2b0d429 · outbound

This paper cites AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.261208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ecd295a-6107-4aa3-9682-247e5b5f1aa8 · outbound

This paper cites Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.373214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79ee3035-118a-407b-8085-916f7b3b6269 · outbound

This paper cites DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.480555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14348ef6-23eb-4fc7-95c7-32497fdfcd76 · outbound

This paper cites Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.561131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4996865d-87dd-432e-bb2b-4d92ae4f1f62 · outbound

This paper cites CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.641624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ec4bc9c-2de1-4dc3-b8e1-8a9345ed3384 · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.726264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eccfcfc-c96a-4ec0-9160-2dc7dcd13a09 · outbound

This paper cites A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.813666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75e46ad7-42c9-47ad-9012-227974bb1b5c · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:40.900099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5062fa6e-774e-4d32-9460-93e018b24fd0 · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.015324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503994c0-873c-4d01-bc23-7d6f96f3ef5c · outbound

This paper cites Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.107700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b527fb2d-3981-4b5b-8a4a-fea67a2d4492 · outbound

This paper cites Harris, and Marcel Carlsson.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Harris, and Marcel Carlsson

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.204266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9b37606-de90-4af1-a6e7-3428a4bc4d79 · outbound

This paper cites Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.267214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a35bf87d-fa26-4e8b-bd01-a5cef0f76913 · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.373394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9741435e-9d62-4bda-8b93-9ddb7eaf1513 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.449950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e071d78-c297-4a80-8084-43d8cac74c4f · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.559678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203f472a-cddb-40ee-9ce1-98549ebf1a3e · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Masterkey: Automated jailbreaking of large language model chatbots

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.666187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a625e3c-4afa-4f3b-b1e3-eb81901693df · outbound

This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.745657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a686db4-7f0f-4504-8970-4b21fbfc98b9 · outbound

This paper cites Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.840089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b336e46-60e1-46ee-b303-d1a7e4301c73 · outbound

This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:41.927775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d6fe14f-9446-49ad-91f7-75c0948f0528 · outbound

This paper cites All in how you ask for it: Simple black-box method for jailbreak attacks.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation All in how you ask for it: Simple black-box method for jailbreak attacks

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:42.032201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3f44fa2-acd8-4f49-8551-f7f32084e4ed · outbound

This paper cites Open Sesame! Universal Black Box Jailbreaking of Large Language Models.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:42.141679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee7830ba-e151-4cca-829e-887234174a10 · outbound

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:42.237749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fdf52f4-855e-4da7-b519-afef192658e4 · outbound

This paper cites Query-Efficient Black-Box Red Teaming via Bayesian Optimization.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Query-Efficient Black-Box Red Teaming via Bayesian Optimization

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:42.328780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers