Jailbreaking Leading Safety-Aligned LLMs: Adaptive Attacks

Research question

How far can simple, model-specific adaptive attacks go against leading models?

Key findings

100% success on GPT-4o, Claude 3 and Llama-3 using prompt templates plus random search on logprobs or prefilling - Trojan-detection and Claude jailbreak challenges won with the same toolbox

Sources

arxiv.orghttps://arxiv.org/abs/2404.02151

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal

Related in Research Paper Library

Mind the Gap: Detecting Description-Execution Mismatch Attacks in DAO Governance

Decentralized autonomous organizations (DAOs) change protocols through a proposal-based process: initiators submit a proposal, members vote on it based on its natural-language description, and if it passes, the…

Adaptive attacks and robustness evaluation2026

Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection

Anomaly-based intrusion detection systems in industrial control systems (ICS) and operational technology (OT) environments are increasingly required to meet formal resilience criteria: absorbed adversarial…

Adaptive attacks and robustness evaluation2026

Robustness Evaluation and Detection of Transferable Adversarial Attacks in ML-Based NIDS

Machine learning-based network intrusion detection systems (ML-based NIDS) are vulnerable to adversarial evasion, where malicious samples are perturbed to evade detection and be misclassified as benign. Despite…

Adaptive attacks and robustness evaluation2026

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Research question

Key findings

Sources

Contribute

Related in Research Paper Library

Mind the Gap: Detecting Description-Execution Mismatch Attacks in DAO Governance

Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection

Robustness Evaluation and Detection of Transferable Adversarial Attacks in ML-Based NIDS