This content will become publicly available on January 26, 2027

Title: JULI: Jailbreak Large Language Models by Self-Introspection
Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as necessitating access to the model weights or the generation process. Since proprietary models through API-calling do not grant users such permissions, these attacks find it challenging to compromise them. In this paper, we propose Jailbreaking Using LLM Introspection (JULI), which jailbreaks LLMs by manipulating the token log probabilities, using a tiny plug-in block, BiasNet. JULI relies solely on the knowledge of the target LLM's predicted token log probabilities. It can effectively jailbreak API-calling LLMs under a black-box setting and knowing only top- token log probabilities. Our approach demonstrates superior effectiveness, outperforming existing state-of-the-art (SOTA) approaches across multiple metrics.  more » « less
Award ID(s):
2229876
PAR ID:
10715212
Author(s) / Creator(s):
; ;
Publisher / Repository:
14th International Conference on Learning Representations (ICLR 2026)
Date Published:
Subject(s) / Keyword(s):
Location:
Rio De Janeiro, Brazil
Sponsoring Org:
National Science Foundation
More Like this
  1. As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses to user queries. Our insight in developing SafeDecoding is based on the observation that, even though probabilities of tokens representing harmful contents outweigh those representing harmless responses, safety disclaimers still appear among the top tokens after sorting tokens by probability in descending order. This allows us to mitigate jailbreak attacks by identifying safety disclaimers and amplifying their token probabilities, while simultaneously attenuating the probabilities of token sequences that are aligned with the objectives of jailbreak attacks. We perform extensive experiments on five LLMs using six state-of-the-art jailbreak attacks and four benchmark datasets. Our results show that SafeDecoding significantly reduces attack success rate and harmfulness of jailbreak attacks without compromising the helpfulness of responses to benign user queries while outperforming six defense methods. Our code is publicly available at: https://github.com/uw-nsl/SafeDecoding 
    more » « less
  2. The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to train or fine-tune these LLMs is often undisclosed, allowing an attacker to compromise the data and inject backdoors into the models. In this paper, we develop a novel inference time defense, named CLEANGEN, to mitigate backdoor attacks for generation tasks in LLMs. CLEANGEN is a lightweight and effective decoding strategy that is compatible with the state-of-the-art (SOTA) LLMs. Our insight behind CLEANGEN is that compared to other LLMs, back doored LLMs assign significantly higher probabilities to tokens representing the attacker-desired contents. These discrepancies in token probabilities enable CLEANGEN to identify suspicious tokens favored by the attacker and replace them with tokens generated by another LLM that is not compromised by the same attacker, thereby avoiding generation of attacker-desired content. We evaluate CLEANGEN against five SOTA backdoor attacks. Our results show that CLEANGEN achieves lower attack success rates (ASR) compared to five SOTA baseline defenses for all five backdoor attacks. Moreover, LLMs deploying CLEANGEN maintain helpfulness in their responses when serving benign user queries with minimal added computational overhead. 
    more » « less
  3. As LLMs become increasingly prevalent across various applications, it is critical to establish safety guardrails to moderate input/output content of LLMs. Existing guardrail models treat various safety categories independently and fail to explicitly capture the intercorrelations among them. This has led to limitations such as ineffectiveness due to inadequate training on long-tail data from correlated safety categories, susceptibility to jailbreaking attacks, and inflexibility regarding new safety categories. To address these limitations, we propose R2-Guard, a robust reasoning enabled LLM guardrail via knowledge-enhanced logical reasoning. Specifically, R2-Guard comprises two parts: data-driven category-specific learning and reasoning components. The data-driven guardrail models provide unsafety probabilities of moderated content on different safety categories. We then encode safety knowledge among different categories as first-order logical rules and embed them into a probabilistic graphic model (PGM) based reasoning component. The unsafety probabilities of different categories from data-driven guardrail models are sent to the reasoning component for final inference. We employ two types of PGMs: Markov logic networks (MLNs) and probabilistic circuits (PCs), and optimize PCs to achieve precision-efficiency balance via improved graph structure. To further perform stress tests for guardrail models, we employ a pairwise construction method to construct a new safety benchmark TwinSafety, which features principled categories. We demonstrate the effectiveness of R2-Guard by comparisons with eight strong guardrail models on six safety benchmarks, and demonstrate the robustness of R2-Guard against four SOTA jailbreaking attacks. R2-Guard significantly surpasses SOTA method LlamaGuard by 30.2% on ToxicChat and by 59.5% against jailbreaking attacks. 
    more » « less
  4. As LLMs become increasingly prevalent across various applications, it is critical to establish safety guardrails to moderate input/output content of LLMs. Existing guardrail models treat various safety categories independently and fail to explicitly capture the intercorrelations among them. This has led to limitations such as ineffectiveness due to inadequate training on long-tail data from correlated safety categories, susceptibility to jailbreaking attacks, and inflexibility regarding new safety categories. To address these limitations, we propose R2-Guard, a robust reasoning enabled LLM guardrail via knowledge-enhanced logical reasoning. Specifically, R2-Guard comprises two parts: data-driven category-specific learning and reasoning components. The data-driven guardrail models provide unsafety probabilities of moderated content on different safety categories. We then encode safety knowledge among different categories as first-order logical rules and embed them into a probabilistic graphic model (PGM) based reasoning component. The unsafety probabilities of different categories from data-driven guardrail models are sent to the reasoning component for final inference. We employ two types of PGMs: Markov logic networks (MLNs) and probabilistic circuits (PCs), and optimize PCs to achieve precision-efficiency balance via improved graph structure. To further perform stress tests for guardrail models, we employ a pairwise construction method to construct a new safety benchmark TwinSafety, which features principled categories. We demonstrate the effectiveness of R2-Guard by comparisons with eight strong guardrail models on six safety benchmarks, and demonstrate the robustness of R2-Guard against four SOTA jailbreaking attacks. R2-Guard significantly surpasses SOTA method LlamaGuard by 30.2% on ToxicChat and by 59.5% against jailbreaking attacks. 
    more » « less
  5. Making large language models (LLMs) safe for mass deployment is a complex and ongoing challenge. Efforts have focused on aligning models to human preferences (RLHF), essentially embedding a “safety feature” into the model’s parameters. The Greedy Coordinate Gradient (GCG) algorithm (Zou et al., 2023b) emerges as one of the most popular automated jailbreaks, an attack that circumvents this safety training. So far, it is believed that such optimization-based attacks (unlike hand-crafted ones) are sample-specific. To make them universal and transferable, one has to incorporate multiple samples and models into the objective function. Contrary to this belief, we find that the adversarial prompts discovered by such optimizers are inherently prompt-universal and transferable, even when optimized on a single model and a single harmful request. To further exploit this phenomenon, we introduce IRIS, a new objective to these optimizers to explicitly deactivate the safety feature to create an even stronger universal and transferable attack. Without requiring a large number of queries or accessing output token probabilities, our universal and transferable attack achieves a 25% success rate against the state-of-the-art Circuit Breaker defense (Zou et al., 2024), compared to 2.5% by white-box GCG. Crucially, IRIS also attains state-of-the-art transfer rates on frontier models: GPT-3.5-Turbo (90%), GPT-4o-mini (86%), GPT-4o (76%), o1-mini (54%), o1-preview (48%), o3-mini (66%), and deepseek-reasoner (90%). 
    more » « less