REVIEW 7 cited by
Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
To ensure AI safety, instruction-tuned Large Language Models (LLMs) are specifically trained to ensure alignment, which refers to making models behave in accordance with human intentions. While these models have demonstrated commendable results on various safety benchmarks, the vulnerability of their safety alignment has not been extensively studied. This is particularly troubling given the potential harm that LLMs can inflict. Existing attack methods on LLMs often rely on poisoned training data or the injection of malicious prompts. These approaches compromise the stealthiness and generalizability of the attacks, making them susceptible to detection. Additionally, these models often demand substantial computational resources for implementation, making them less practical for real-world applications. In this work, we study a different attack scenario, called Trojan Activation Attack (TA^2), which injects trojan steering vectors into the activation layers of LLMs. These malicious steering vectors can be triggered at inference time to steer the models toward attacker-desired behaviors by manipulating their activations. Our experiment results on four primary alignment tasks show that TA^2 is highly effective and adds little or no overhead to attack efficiency. Additionally, we discuss potential countermeasures against such activation attacks.
Forward citations
Cited by 7 Pith papers
-
Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
A trigger-tag watermark embedded by fine-tuning lets modified LLMs mark their own phishing outputs for cheap detection.
-
Steering Protein Language Models
Activation steering can guide protein language models to generate and optimize sequences with higher predicted thermostability, solubility, or GFP brightness, but only in surrogate-based evaluation.
-
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
ROSI bakes the refusal direction into a model's weight matrices via a rank-one update, raising refusal and jailbreak robustness with minimal measured utility cost.
-
Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.
-
Security Concerns for Large Language Models: A Survey
A survey that classifies LLM security threats and argues that intrinsic agentic risks, such as scheming, are underappreciated and poorly defended.
-
Probing the Robustness of Large Language Models Safety to Latent Perturbations
Randomized noise injected into hidden layers bypasses safety refusals in 12 open LLMs, and layer-wise adversarial training on the resulting benchmark reduces the attack's success.
-
Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
A survey categorizing prompt-based attacks on LLMs into four classes and proposing aspirational goals of un-distillable, un-finetunable, and un-editable models.
Discussion (0). Continue with ORCID to comment.