The proliferation of powerful large language models (LLMs) has necessitated robust safety alignment, yet these models remain vulnerable to evolving adversarial attacks, including multi-turn jailbreaks that iteratively search for successful queries. Current defenses, which are primarily reactive and static, often fail to handle these iterative attacks. In this paper, we introduce ProAct, a novel proactive defense framework designed to disrupt and mislead these iterative search jailbreak methods. Our core idea is to intentionally mislead these jailbreak methods into thinking that the model has been jailbroken with "spurious responses". These misleading responses provide false signals to the attacker’s internal optimization loop, causing the adversarial search to terminate prematurely and effectively jailbreaking the jailbreak. By conducting extensive experiments across state-of-the-art LLMs, jailbreaking frameworks, and safety benchmarks, we demonstrate that our method consistently and significantly reduces attack success rates by up to 94% without affecting utility. When combined with other defense frameworks, it further reduces the latest attack strategies’ success rate to 0%. ProAct represents an orthogonal defense strategy that serves as an additional guardrail to enhance LLM safety against the most effective jailbreaking attacks.

We have uncovered a powerful jailbreak technique that leverages large language models’ ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate and obfuscate previous attacks, our method dramatically outperforms existing approaches, achieving up to a 62.83% higher success rate in compromising ten leading chatbots, including GPT-4, Gemini, and Llama, while using only 12.9% of the queries. This revelation exposes a critical flaw in current LLM safety training, suggesting that existing methods may merely mask vulnerabilities rather than eliminate them. Our findings sound an urgent alarm for the need to revolutionize testing methodologies to ensure robust and reliable LLM security.

Detecting text generated by Large Language Models (LLMs) is crucial, yet current detectors often struggle to generalize in open-world settings. We introduce Learning2Rewrite, a novel framework to detect LLM-generated text with exceptional generalization to unseen domains. Capitalized on the finding that LLMs inherently modify LLM-generated content less than human-written text when rewriting, we train an LLM to amplify this disparity, yielding a more distinguishable and generalizable edit distance across diverse text distributions. Extensive experiments on data from 21 independent domains and four major LLMs (GPT-3.5, GPT-4, Gemini, and Llama-3) demonstrate that our detector outperforms state-of-the-art detection methods by up to 23.04% in AUROC for in-distribution tests, 35.10% for out-of-distribution tests, and 48.66% under adversarial attacks. Our unique training objective ensures better generalizability compared to directly training for classification, even when leveraging the same amount of tunable parameters. Our findings suggest that reinforcing LLMs’ inherent rewriting tendencies offers a robust and scalable solution for detecting LLM-generated text.