Pith. sign in

Paper Citation Record · LEDGER

Poisoning and Backdooring Contrastive Learning

As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2106.09667.

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

pith.paper-citation-record.v1
2106.09667 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T18:22:17.115586Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T15:47:23.362197Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 5ead7bf7-1479-4e17-890c-1d1bf66755a3 · inbound

Unsolved Problems in ML Safety cites this paper.

Unsolved Problems in ML Safety Poisoning and Backdooring Contrastive Learning

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-05-16T20:45:27.564378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-05-16T20:45:27.421909Z digest=sha256:2fd39f9cc0e4e39c79894e862a58888f7d68275ec16c35c12171c4f1efc10daf

Observation 5d5d74ee-b597-48e4-aa6b-82b284c6613d · inbound

The Curse of Recursion: Training on Generated Data Makes Models Forget cites this paper.

The Curse of Recursion: Training on Generated Data Makes Models Forget Poisoning and Backdooring Contrastive Learning

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-05-20T14:04:58.294130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-05-20T14:04:58.271168Z digest=sha256:3ecbf87aa5bf7820a06fdb8e19db4eac8d5a801a7a8dea625435639cffe793c2

Observation 29372726-8789-46f3-9bae-0e4d3358b92a · inbound

Dissecting Representation Misalignment in Contrastive Learning via Influence Function cites this paper.

Dissecting Representation Misalignment in Contrastive Learning via Influence Function Poisoning and Backdooring Contrastive Learning

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-12T18:22:17.115586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T18:22:17.115586Z digest=sha256:8a510ecaf79bcb6e4ea8ad6ccf9a881090f916b13643abaa7f42465de3f0977c

Observation 63fb8c9d-79b0-4246-ae67-9fe61f2e6611 · inbound

DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders cites this paper.

DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders Poisoning and Backdooring Contrastive Learning

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-12T13:33:16.558896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T13:33:16.558896Z digest=sha256:937e81aef6f532fe6443b30fc5311af0008903c228b7737740e77fc896c8c6c2

Observation ba346b80-3f98-4efd-8ce4-b5c84b405014 · inbound

Data Free Backdoor Attacks cites this paper.

Data Free Backdoor Attacks Poisoning and Backdooring Contrastive Learning

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-11T20:00:29.006260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T20:00:29.006260Z digest=sha256:069a6add4412425b19e4210e3273df2087f59688d87b45fdc68262714aae0b85

Observation 29722ffc-be97-4254-8d91-47cc520302c8 · inbound

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs cites this paper.

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs Poisoning and Backdooring Contrastive Learning

Reference 102

Resolution
unresolved
no resolver link, observed 2026-08-08T15:38:17.461082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T15:38:17.461082Z digest=sha256:c6cebf87e500fe9a6cce00e17fd1f29dbde0a1469ac47f0076236a95f2f6a9ab

Observation ff540755-1573-41a5-8827-62742ce53bf4 · inbound

Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise cites this paper.

Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise Poisoning and Backdooring Contrastive Learning

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T12:13:21.984002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:13:21.984002Z digest=sha256:275838e571f39c7a3717a0ebf064d57d411d1d12abcafb465626544f5ba150f0

Observation c4235e0e-a63f-4fd9-8c7e-d8bef52a7dc3 · inbound

M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration cites this paper.

M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration Poisoning and Backdooring Contrastive Learning

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T05:27:56.879680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:27:56.879680Z digest=sha256:7234e4c48bfb124c227a1bff419ed92e03001e34911865e9ea4f3e02a28f67ed

Observation 8aad8d34-8065-4653-8463-0e9ff7c17d03 · inbound

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning cites this paper.

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning Poisoning and Backdooring Contrastive Learning

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T00:58:06.354452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:58:06.354452Z digest=sha256:c52a7651b59cd13f2c7b5ab5a40b34101504028ed4b9722f4b0faf1b9518c673

Observation d41e1f75-631f-4e90-b94e-fc52992186b3 · inbound

Dataset Ownership Verification for Pre-trained Masked Models cites this paper.

Dataset Ownership Verification for Pre-trained Masked Models Poisoning and Backdooring Contrastive Learning

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T17:04:33.541225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:04:33.541225Z digest=sha256:e6cfed040daeb285a3817bcea26202d323b9ccce272998c07b1a7c90bd463d00

Observation f0432415-65b2-4fe6-8bd5-60beead500a0 · inbound

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) cites this paper.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Poisoning and Backdooring Contrastive Learning

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-05T15:18:29.850429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:18:29.850429Z digest=sha256:c95c54531d3e558ccb5d176e5656a6083e38210cb1b45fbe4f6cf79630672f9c

Observation 0a847a5e-b5f2-4092-a641-43206b7049ed · inbound

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems cites this paper.

VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems Poisoning and Backdooring Contrastive Learning

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-03T04:00:15.950868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T04:00:15.950868Z digest=sha256:0c46fb55c371ba4392a00fc77f9cf5fc08ead81e56b6d4eb545b07447f1a3a36

Observation e529afbc-f225-445c-9695-0d2094fbc18f · inbound

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models cites this paper.

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models Poisoning and Backdooring Contrastive Learning

Reference 25

Resolution
verified exact
arxiv_id, observed 2026-05-10T22:15:51.378052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-05-10T20:01:57.909924Z digest=sha256:bf42acfca0bf40ec2e12572414fec73cac41997a310d2013af5028b21614fe3b

Observation c8c2fd30-2ae1-4207-a750-73a9b582501b · inbound

The Grand Software Supply Chain of AI Systems cites this paper.

The Grand Software Supply Chain of AI Systems Poisoning and Backdooring Contrastive Learning

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-12T10:16:27.654956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-05-07T06:54:21.194128Z digest=sha256:56fe4817288efac171471d0bfad0110c98381b25906b410733407022cca2afaa

Observation 8013685c-4359-4c20-942d-045bfc104897 · inbound

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks cites this paper.

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks Poisoning and Backdooring Contrastive Learning

Reference 289

Resolution
verified exact
local_arxiv, observed 2026-07-10T15:47:23.363371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-07-10T15:38:58.361411Z digest=sha256:64575677c40eca16f2da3a03ae5f12f9c43dd1eea36f17ebd8bc448f6ad59e21

Observation 80e2d0b9-4618-42fe-a54d-b8bc2845d1d9 · inbound

Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs cites this paper.

Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs Poisoning and Backdooring Contrastive Learning

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-12T13:30:42.582232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-12T13:30:42.582232Z digest=sha256:c9d8ef1c58a131b91d1bd6b3448b078f931f69ef116385acaedad167b3bd850d