REVIEW 6 cited by
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
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
Despite careful safety alignment, current large language models (LLMs) remain vulnerable to various attacks. To further unveil the safety risks of LLMs, we introduce a Safety Concept Activation Vector (SCAV) framework, which effectively guides the attacks by accurately interpreting LLMs' safety mechanisms. We then develop an SCAV-guided attack method that can generate both attack prompts and embedding-level attacks with automatically selected perturbation hyperparameters. Both automatic and human evaluations demonstrate that our attack method significantly improves the attack success rate and response quality while requiring less training data. Additionally, we find that our generated attack prompts may be transferable to GPT-4, and the embedding-level attacks may also be transferred to other white-box LLMs whose parameters are known. Our experiments further uncover the safety risks present in current LLMs. For example, in our evaluation of seven open-source LLMs, we observe an average attack success rate of 99.14%, based on the classic keyword-matching criterion. Finally, we provide insights into the safety mechanism of LLMs. The code is available at https://github.com/SproutNan/AI-Safety_SCAV.
Forward citations
Cited by 6 Pith papers
-
Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
Alignment on Llama 3 reduces explicit bias but amplifies implicit bias, because aligned models no longer represent 'black' and 'white' as racial concepts in ambiguous contexts.
-
The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
Reliable concept presence in transformers is concentrated in the extreme high-activation tail of in-concept tokens; thresholding that tail improves concept detection and localization.
-
Probing the Difficulty Perception Mechanism of Large Language Models
LLMs linearly encode math-problem difficulty in their final-token representations, and specific final-layer attention heads are specialized for easy vs hard problems.
-
Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks
IMAGINE pre-synthesizes intent-concealed jailbreak-like instructions via iterative latent-space expansion, and DPO with that data reduces jailbreak attack success rates on Qwen2.5, Llama3.1 and Llama3.2.
-
Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
ConVA identifies value-specific directions in an LLM's internal activations from context-matched GPT-4o-generated examples and gates minimal activation steering to control outputs across ten Schwartz values.
-
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.
Discussion (0). Sign in to comment.