Search papers, labs, and topics across Lattice.
This paper introduces Adversarial Prompt Disentanglement (APD), a framework that decomposes input prompts into statistically independent adversarial and benign components using mutual information. APD then employs spectral analysis on a semantic graph to classify the intent of these components, coupled with a lightweight transformer for efficient adversarial detection. Experiments show APD reduces harmful LLM outputs by 85% with minimal performance impact, suggesting a viable defense against prompt-based attacks.
LLM defenses don't have to sacrifice performance: APD disentangles adversarial prompts to slash harmful outputs by 85% while maintaining model utility.
Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and availability of LLMs in security-critical applications. This paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense mechanism that proactively identifies and neutralizes malicious components in input prompts before they are processed by the LLM. The APD framework integrates three key innovations: (1) a mutual information- based semantic decomposition method to isolate adversarial and benign prompt components, ensuring statistical in- dependence; (2) a graph-based intent classification approach that leverages spectral analysis to detect malicious patterns in prompt semantics; and (3) a lightweight transformer-based classifier trained on real-world datasets of toxic and jailbreaking prompts, enabling efficient and accurate adversarial intent detection. Evaluated on diverse datasets containing adversarial prompts, APD demonstrates superior robustness, reducing harmful output generation by over 85% while maintaining negligible impact on model performance. The framework鈥檚 computational efficiency supports real-time deploy- ment, making it a practical solution for securing LLMs. Our work addresses critical challenges in machine learning security on novel attacks and integrity methods for ML systems, and offers a scalable, ethically grounded defense against prompt-based adversarial threats.
