Paper Citation Record · LEDGER

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 22 inbound Pith citation observations for arXiv:2311.09433.

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

pith.paper-citation-record.v1
2311.09433 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 22 of 22 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:38:51.896624Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T00:27:29.192379Z

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 3a09ebe2-8c9d-406f-af79-8900035ef1a4 · inbound

Refusal in Language Models Is Mediated by a Single Direction cites this paper.

Refusal in Language Models Is Mediated by a Single Direction Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 194

Resolution: verified exact; arxiv_id, observed 2026-05-13T10:47:56.141141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 42c003f5-cb69-47c0-9099-d328c904716e · inbound

AgentReview: Exploring Peer Review Dynamics with LLM Agents cites this paper.

AgentReview: Exploring Peer Review Dynamics with LLM Agents Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-23T23:38:37.121335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ebb851fd-c435-49bb-a464-ee806890944b · inbound

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey cites this paper.

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 155

Resolution: verified exact; arxiv_id, observed 2026-05-23T20:58:26.320120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 63f11b28-45ac-4144-844b-1c0a5b001817 · inbound

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations cites this paper.

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T17:20:47.932852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d93e93e-2304-431b-867b-c035a315f234 · inbound

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs cites this paper.

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 136

Resolution: unresolved; no resolver link, observed 2026-08-10T23:40:19.111201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a8eaf54-aad6-4d17-9a68-39953e2e431d · inbound

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning cites this paper.

Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T20:35:52.848329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd41a068-d301-48c4-a177-4c4270a48e03 · inbound

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities cites this paper.

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-09T14:47:15.367750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e77078-dd1c-41f3-9ab2-6c2cbbe4139d · inbound

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations cites this paper.

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 138

Resolution: unresolved; no resolver link, observed 2026-08-09T00:50:00.594555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d030c5a8-2651-4432-b2c9-9454504a4bba · inbound

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts cites this paper.

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T10:38:51.896624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbefdb4a-f310-4c2a-98cd-b930afcfbb91 · inbound

A Survey of Attacks on Large Language Models cites this paper.

A Survey of Attacks on Large Language Models Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:34:34.367090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0edccbc-9058-4a21-ab17-e03d4e0de2a8 · inbound

Improving Multilingual Language Models by Aligning Representations through Steering cites this paper.

Improving Multilingual Language Models by Aligning Representations through Steering Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.342800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15125eaa-6240-4c15-bf31-a7767070f8d6 · inbound

Security Concerns for Large Language Models: A Survey cites this paper.

Security Concerns for Large Language Models: A Survey Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:03.694102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b6adedc-a47d-4cdd-96cd-7504bbb58849 · inbound

Probing the Robustness of Large Language Models Safety to Latent Perturbations cites this paper.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:17.484246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

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 fdcaea98-406f-4a1e-8a4a-c9766de5394c · inbound

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection cites this paper.

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T14:57:12.929314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4166b559-ecfe-405c-863f-59b3cf19d032 · inbound

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs cites this paper.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.669109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70146f0-2fba-4554-9a18-c148d61dcb7e · inbound

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs cites this paper.

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T05:59:28.741450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 392ef71b-f54a-460c-9979-0a6a0328f509 · inbound

Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm cites this paper.

Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T22:33:23.762799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669b354d-6352-46b5-ae79-5dd23e4f80a3 · inbound

Steering Protein Language Models cites this paper.

Steering Protein Language Models Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:12.120075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df99dcde-4a01-4892-a680-119eedabcf21 · inbound

On the Privacy of LLMs: An Ablation Study cites this paper.

On the Privacy of LLMs: An Ablation Study Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:25:48.822645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 78740697-7847-4edf-8364-1f2f8a477cf4 · inbound

Distilling Safe LLM Systems via Soft Prompts for On Device Settings cites this paper.

Distilling Safe LLM Systems via Soft Prompts for On Device Settings Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 70

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:27:29.194109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ad231733-d94c-49a6-a5d4-45e21278f74c · inbound

Evading Chain-of-Thought Monitoring Through Model Poisoning cites this paper.

Evading Chain-of-Thought Monitoring Through Model Poisoning Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.284542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.