Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
Large Language Models (LLMs), especially those accessed via APIs, have demonstrated impressive capabilities across various domains. However, users without technical expertise often turn to (untrustworthy) third-party services, such as prompt engineering, to enhance their LLM experience, creating vulnerabilities to adversarial threats like backdoor attacks. Backdoor-compromised LLMs generate malicious outputs to users when inputs contain specific "triggers" set by attackers. Traditional defense strategies, originally designed for small-scale models, are impractical for API-accessible LLMs due to limited model access, high computational costs, and data requirements. To address these limitations, we propose Chain-of-Scrutiny (CoS) which leverages LLMs' unique reasoning abilities to mitigate backdoor attacks. It guides the LLM to generate reasoning steps for a given input and scrutinizes for consistency with the final output -- any inconsistencies indicating a potential attack. It is well-suited for the popular API-only LLM deployments, enabling detection at minimal cost and with little data. User-friendly and driven by natural language, it allows non-experts to perform the defense independently while maintaining transparency. We validate the effectiveness of CoS through extensive experiments on various tasks and LLMs, with results showing greater benefits for more powerful LLMs.
Code (1)
Tasks
Prompt EngineeringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Evaluating Neural Network Backdoor Defenses
Deep neural networks (DNNs) demonstrate superior performance in various fields, including scrutiny and security. However, recent studies have shown that DNNs are vulnerable to backdoor attacks. Several defenses were prop…
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fixed words, phrases, or sentences used in …
Text ClassificationText GenerationBadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulne…
Backdoor AttackShortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely o…
Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
Pre-trained models (PTMs) are widely adopted across various downstream tasks in the machine learning supply chain. Adopting untrustworthy PTMs introduces significant security risks, where adversaries can poison the model…
Backdoor Attack