Paper Library

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Zonghao Ying, Siyang Wu, Run Hao, Peng Ying, Shixuan Sun, Pengyu Chen, Junze Chen, Hao Du, Kaiwen Shen, Shangkun Wu, Jiwei Wei, Shiyuan He, Yang Yang, Xiaohai Xu, Ke Ma, Qianqian Xu, Qingming Huang, Shi Lin, Xun Wang, Changting Lin, Meng Han, Yilei Jiang, Siqi Lai, Yaozhi Zheng, Yifei Song, Xiangyu Yue, Zonglei Jing, Tianyuan Zhang, Zhilei Zhu, Aishan Liu, Jiakai Wang, Siyuan Liang, Xianglong Kong, Hainan Li, Junjie Mu, Haotong Qin, Yue Yu, Lei Chen, Felix Juefei-Xu, Qing Guo, Xinyun Chen, Yew Soon Ong, Xianglong Liu, Dawn Song, Alan Yuille, Philip Torr, Dacheng Tao

2025-06-14

red teaming

2506.12430v1

June 23 - June 29, 2025

NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation

June 16 - June 22, 2025

Multi-turn Jailbreaking via Global Refinement and Active Fabrication

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers

MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Probing the Robustness of Large Language Models Safety to Latent Perturbations

deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts

LLM Jailbreak Oracle

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions

Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-AI Interactions

Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs

June 09 - June 15, 2025

Jailbreak Strength and Model Similarity Predict Transferability

Universal Jailbreak Suffixes Are Strong Attention Hijackers

Governments Should Mandate Tiered Anonymity on Social-Media Platforms to Counter Deepfakes and LLM-Driven Mass Misinformation

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025