SOTAVerified

LLM Jailbreak

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–24 of 24 papers

TitleStatusHype
Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered CluesCode2
JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language ModelsCode2
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking AttacksCode2
JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak AttacksCode2
CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language ModelsCode1
Automatic Prompt Optimization with "Gradient Descent" and Beam SearchCode1
Cognitive Overload Attack:Prompt Injection for Long ContextCode1
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response—0
DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak—0
Efficient Indirect LLM Jailbreak via Multimodal-LLM Jailbreak—0
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks—0
Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack—0
Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles—0
HSF: Defending against Jailbreak Attacks with Hidden State Filtering—0
LLM Jailbreak Oracle—0
POEX: Understanding and Mitigating Policy Executable Jailbreak Attacks against Embodied AI—0
SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression—0
Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models—0
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner—0
Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content ModerationCode0
CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal RepresentationsCode0
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained OptimizationCode0
SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical SynthesisCode0
SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task LinkageCode0
Show:102550

No leaderboard results yet.