CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful attacks, introducing a hypothesis for the safety mechanism of aligned LLMs: intent security recognition followed by response generation. Grounded in this hypothesis, we propose CodeChameleon, a novel jailbreak framework based on personalized encryption tactics. To elude the intent security recognition phase, we reformulate tasks into a code completion format, enabling users to encrypt queries using personalized encryption functions. To guarantee response generation functionality, we embed a decryption function within the instructions, which allows the LLM to decrypt and execute the encrypted queries successfully. We conduct extensive experiments on 7 LLMs, achieving state-of-the-art average Attack Success Rate (ASR). Remarkably, our method achieves an 86.6\% ASR on GPT-4-1106.
Code (1)
Tasks
Code CompletionResponse GenerationSimilar Papers 제목 키워드 기반
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
Recent advancements in the safety of Large Language Models (LLMs) have primarily focused on mitigating attacks crafted in natural language or in common encryption techniques like Base64. However, new models which often p…
Benchmarking Large Language Models for Cryptanalysis and Mismatched-Generalization
Recent advancements in Large Language Models (LLMs) have transformed natural language understanding and generation, leading to extensive benchmarking across diverse tasks. However, cryptanalysis a critical area for data …
BenchmarkingCryptanalysisNatural Language UnderstandingEncryption-Friendly LLM Architecture
Large language models (LLMs) offer personalized responses based on user interactions, but this use case raises serious privacy concerns. Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic compu…
Privacy PreservingSecure On-Device Video OOD Detection Without Backpropagation
Out-of-Distribution (OOD) detection is critical for ensuring the reliability of machine learning models in safety-critical applications such as autonomous driving and medical diagnosis. While deploying personalized OOD d…
Autonomous DrivingFederated LearningMedical DiagnosisOut of Distribution (OOD) DetectionAdaptive Jailbreaking Strategies Based on the Semantic Understanding Capabilities of Large Language Models
Adversarial attacks on Large Language Models (LLMs) via jailbreaking techniques-methods that circumvent their built-in safety and ethical constraints-have emerged as a critical challenge in AI security. These attacks com…