Haoxuan Ji

Zheng Lin, Zhenxing Niu, Haoxuan Ji et al.

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a model's internal reasoning process introduces additional safety risks; for example, recent studies show that LRMs are more vulnerable to jailbreak attacks than standard LLMs. In this paper, we investigate jailbreak attacks on LRMs and reveal that the attack success rate (ASR) is closely correlated with LRMs' attention patterns. Specifically, successful jailbreaks tend to assign lower attention to harmful tokens in the input prompt, while allocating higher attention to those tokens in the reasoning content. Motivated by this finding, we propose a novel jailbreak method for LRMs that leverages reinforcement learning (RL) to enhance attack effectiveness, explicitly incorporating attention signals into the reward function design. In addition, we introduce diverse persuasion strategies to enrich the RL action space, which consistently improves the ASR. Extensive experiments on five open-source and closed-source LRMs across three benchmarks demonstrate that our method achieves substantially higher ASR, outperforming existing approaches in terms of effectiveness, efficiency, and transferability.

Yuhang Wang, Zhenxing Niu, Haoxuan Ji et al.

The core challenge of machine unlearning is to strike a balance between target knowledge removal and non-target knowledge retention. In the context of Multimodal Large Language Models (MLLMs), this challenge becomes even more pronounced, as knowledge is further divided into visual and textual modalities that are tightly intertwined. In this paper, we introduce an MLLM unlearning approach that aims to forget target visual knowledge while preserving non-target visual knowledge and all textual knowledge. Specifically, we freeze the LLM backbone and achieve unlearning by fine-tuning the visual module. First, we propose a Contrastive Visual Forgetting (CVF) mechanism to separate target visual knowledge from retained visual knowledge, guiding the representations of target visual concepts toward appropriate regions in the feature space. Second, we identify the null space associated with retained knowledge and constrain the unlearning process within this space, thereby significantly mitigating degradation in knowledge retention. Third, beyond static unlearning scenarios, we extend our approach to continual unlearning, where forgetting requests arrive sequentially. Extensive experiments across diverse benchmarks demonstrate that our approach achieves a strong balance between effective forgetting and robust knowledge retention.

Ningnan Wang, Weihuang Chen, Liming Chen et al.

Embodied visual navigation remains a challenging task, as agents must explore unknown environments with limited knowledge. Existing zero-shot studies have shown that incorporating memory mechanisms to support goal-directed behavior can improve long-horizon planning performance. However, they overlook visual frontier boundaries, which fundamentally dictate future trajectories and observations, and fall short of inferring the relationship between partial visual observations and navigation goals. In this paper, we propose Semantic Cognition Over Potential-based Exploration (SCOPE), a zero-shot framework that explicitly leverages frontier information to drive potential-based exploration, enabling more informed and goal-relevant decisions. SCOPE estimates exploration potential with a Vision-Language Model and organizes it into a spatio-temporal potential graph, capturing boundary dynamics to support long-horizon planning. In addition, SCOPE incorporates a self-reconsideration mechanism that revisits and refines prior decisions, enhancing reliability and reducing overconfident errors. Experimental results on two diverse embodied navigation tasks show that SCOPE outperforms state-of-the-art baselines by 4.6\% in accuracy. Further analysis demonstrates that its core components lead to improved calibration, stronger generalization, and higher decision quality.

Zheng Lin, Zhenxing Niu, Haoxuan Ji et al.

This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel smoothing-based defense method, termed Disrupt-and-Rectify Smoothing (DR-Smoothing). Specifically, we integrate a two-stage prompt processing scheme-first disrupting the input prompt, then rectifying it-into the conventional smoothing defense framework. This disrupt-and-rectify approach improves upon previous disrupt-only approaches by restoring out-of-distribution disrupted prompts to an in-distribution form, thereby reducing the risk of unpredictable LLM behavior. In addition, this two-stage scheme offers a distinct advantage in striking a balance between harmlessness and helpfulness in jailbreaking defense. Notably, we present a theoretical analysis for generic smoothing framework, offering a tight bound for the defense success probability and the requirements on the disruption strength. Our approach can defend against both token-level and prompt-level jailbreaking attacks, under both established and adaptive attacking scenarios. Extensive experiments demonstrate that our approach surpasses current state-of-the-art defense methods in terms of both harmlessness and helpfulness.

Zheng Lin, Zhenxing Niu, Haoxuan Ji et al.

This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts that bypass them. We argue that such jailbreaking prompts are inherently fragile, and thus introduce an embedding disruption method to re-activate the safeguards within LLMs. Unlike previous defense methods that aim to serve as standalone solutions, our approach instead cooperates with the LLM's internal defense mechanisms by re-triggering them. Moreover, through extensive analysis, we gain a comprehensive understanding of the disruption effects and develop an efficient search algorithm to identify appropriate disruptions for effective jailbreak detection. Extensive experiments demonstrate that our approach effectively defends against state-of-the-art jailbreak attacks in white-box and black-box settings, and remains robust even against adaptive attacks.

Yuhang Wang, Zhenxing Niu, Haoxuan Ji et al.

Recently, machine unlearning approaches have been proposed to remove sensitive information from well-trained large models. However, most existing methods are tailored for LLMs, while MLLM-oriented unlearning remains at its early stage. Inspired by recent studies exploring the internal mechanisms of MLLMs, we propose to disentangle the visual and textual knowledge embedded within MLLMs and introduce a dedicated approach to selectively erase target visual knowledge while preserving textual knowledge. Unlike previous unlearning methods that rely on output-level supervision, our approach introduces a Visual Knowledge Distillation (VKD) scheme, which leverages intermediate visual representations within the MLLM as supervision signals. This design substantially enhances both unlearning effectiveness and model utility. Moreover, since our method only fine-tunes the visual components of the MLLM, it offers significant efficiency advantages. Extensive experiments demonstrate that our approach outperforms state-of-the-art unlearning methods in terms of both effectiveness and efficiency. Moreover, we are the first to evaluate the robustness of MLLM unlearning against relearning attacks.

Haoxuan Ji, Zheng Lin, Yuyao Sun et al.

Modern privacy regulations have spurred the evolution of machine unlearning, a technique that enables the removal of data from an already trained ML model without requiring retraining from scratch. Previous unlearning methods tend to induce the model to achieve lowest classification accuracy on the removal data. Nonetheless, the authentic objective of machine unlearning is to align the unlearned model with the gold model, i.e., achieving the same classification accuracy as the gold model. For this purpose, we present a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem. As a results, the generalization-label predictor trained on the twin problem can be transferred to the original problem, facilitating aligned data removal. Comprehensive empirical experiments illustrate that our approach significantly enhances the alignment between the unlearned model and the gold model. Meanwhile, our method allows data removal without compromising the model accuracy.

Zhenxing Niu, Haoxuan Ji, Yuyao Sun et al.

Modern privacy regulations have spurred the evolution of machine unlearning, a technique enabling a trained model to efficiently forget specific training data. In prior unlearning methods, the concept of "data forgetting" is often interpreted and implemented as achieving zero classification accuracy on such data. Nevertheless, the authentic aim of machine unlearning is to achieve alignment between the unlearned model and the gold model, i.e., encouraging them to have identical classification accuracy. On the other hand, the gold model often exhibits non-zero classification accuracy due to its generalization ability. To achieve aligned data forgetting, we propose a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem. Consequently, the generalization-label predictor trained on the twin problem can be transferred to the original problem, facilitating aligned data forgetting. Comprehensive empirical experiments illustrate that our approach significantly enhances the alignment between the unlearned model and the gold model.