REVIEW 4 cited by
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement
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
Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to respond to fast-developing attacks immediately, such as jailbreaks. We propose self-refine with formatting that achieves outstanding safety even in non-safety-aligned LMs and evaluate our method alongside several defense baselines, demonstrating that it is the safest training-free method against jailbreak attacks. Additionally, we proposed a formatting method that improves the efficiency of the self-refine process while reducing attack success rates in fewer iterations. We've also observed that non-safety-aligned LMs outperform safety-aligned LMs in safety tasks by giving more helpful and safe responses. In conclusion, our findings can achieve less safety risk with fewer computational costs, allowing non-safety LM to be easily utilized in real-world service.
Forward citations
Cited by 4 Pith papers
-
SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
A 24-dataset benchmark for inducing schema graphs from raw text, plus an auditable LLM-based pipeline that reports the highest scores on the benchmark's four schema-similarity metrics.
-
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses
A systemization of LLM jailbreak security that adds linked taxonomies, an evaluation platform, and JailbreakDB, while its main attack–defense comparison results remain deferred.
-
Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
An iterative attacker-defender reinforcement learning method that makes a multimodal LLM refuse more jailbreak prompts without over-refusing ordinary queries.
-
Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness
A systematic benchmark shows multi-agent debate's value depends on task difficulty, model scale, and agent diversity: limited for math unless problems are hard or models weak, but useful for safety when agents are diverse.
Discussion (0). Continue with ORCID to comment.