arXiv AI
SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 23
JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models
arXiv:2607. 19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates.
arXiv AI
Aug 11
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
arXiv:2509. 03985v2 Announce Type: replace-cross Abstract: In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs.
arXiv Computation and Language
Aug 25
Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models
The paper introduces TA-SPA, a black‑box jailbreak method for multimodal large language models that generates transferable perturbations in a text‑anchored semantic space. It combines Text‑Anchored Semantic Factorization (TASF) to separate cross‑modal semantic factors from modality‑specific residuals with Semantic‑Preserving Augmentation (SPA) to diversify harmful target anchors while maintaining semantic consistency. Experiments demonstrate strong attack effectiveness and transferability to commercial MLLMs, with competitive performance against representative defenses.
Hugging Face Trending Papers
Aug 4
ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently emerged as a promising attack paradigm.
arXiv AI
Sep 2
Validity-Aware Jailbreak Evaluation for Large Language Models
The paper introduces SEAV, a verification‑centric framework for evaluating jailbreak attempts against large language models. SEAV decomposes responses into ordered steps and checks both validity and correctness using LLM‑as‑a‑judge and retrieval‑grounded verification. The method reduces false positives by 14.9 percentage points on a strategic‑dishonesty diagnostic and reclassifies 22.1–51.0% of previously successful jailbreaks as invalid across multiple benchmarks.
arXiv AI
Jun 29
MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
arXiv:2510. 10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs).