Pith. sign in

REVIEW 2 cited by

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2502.16776 v1 pith:GBGNPWCA submitted 2025-02-24 cs.CL cs.AI

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement

Zhexin Zhang , Leqi Lei , Junxiao Yang , Xijie Huang , Yida Lu , Shiyao Cui , Renmiao Chen , Qinglin Zhang
show 8 more authors
Xinyuan Wang Hao Wang Hao Li Xianqi Lei Chengwei Pan Lei Sha Hongning Wang Minlie Huang
This is my paper
classification cs.CL cs.AI
keywords aisafetylabsafetyframeworkattackcomprehensivedefenseevaluationimprovement
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have been made to evaluate and enhance AI safety, the lack of a standardized framework and comprehensive toolkit poses significant obstacles to systematic research and practical adoption. To bridge this gap, we introduce AISafetyLab, a unified framework and toolkit that integrates representative attack, defense, and evaluation methodologies for AI safety. AISafetyLab features an intuitive interface that enables developers to seamlessly apply various techniques while maintaining a well-structured and extensible codebase for future advancements. Additionally, we conduct empirical studies on Vicuna, analyzing different attack and defense strategies to provide valuable insights into their comparative effectiveness. To facilitate ongoing research and development in AI safety, AISafetyLab is publicly available at https://github.com/thu-coai/AISafetyLab, and we are committed to its continuous maintenance and improvement.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs

    cs.CR 2026-05 unverdicted novelty 6.0

    A truly benign DPO attack using 10 harmless preference pairs jailbreaks frontier LLMs by suppressing refusal behavior, achieving up to 81.73% attack success rate on GPT-4.1-nano at low cost.

  2. SoK: Robustness in Large Language Models against Jailbreak Attacks

    cs.CR 2026-05 accept novelty 5.0

    The paper taxonomizes jailbreak attacks and defenses for LLMs, introduces the Security Cube multi-dimensional evaluation framework, benchmarks 13 attacks and 5 defenses, and identifies open challenges in LLM robustness.