English
Related papers

Related papers: Segment-Level Coherence for Robust Harmful Intent …

200 papers

This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreak methods that directly orient to LLMs, our…

Artificial Intelligence · Computer Science 2025-12-02 Haoxuan Ji , Zheng Lin , Zhenxing Niu , Xinbo Gao , Gang Hua

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Computation and Language · Computer Science 2026-02-03 Zehua Cheng , Jianwei Yang , Wei Dai , Jiahao Sun

Sequential recommender systems stand out for their ability to capture users' dynamic interests and the patterns of item-to-item transitions. However, the inherent openness of sequential recommender systems renders them vulnerable to…

Information Retrieval · Computer Science 2025-03-03 Kaike Zhang , Qi Cao , Yunfan Wu , Fei Sun , Huawei Shen , Xueqi Cheng

Content moderation remains a critical yet challenging task for large-scale user-generated video platforms, especially in livestreaming environments where moderation must be timely, multimodal, and robust to evolving forms of unwanted…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Wei Chee Yew , Hailun Xu , Sanjay Saha , Xiaotian Fan , Hiok Hian Ong , David Yuchen Wang , Kanchan Sarkar , Zhenheng Yang , Danhui Guan

Jailbreak attack can be used to access the vulnerabilities of Large Language Models (LLMs) by inducing LLMs to generate the harmful content. And the most common method of the attack is to construct semantically ambiguous prompts to confuse…

Cryptography and Security · Computer Science 2025-07-09 Rui Pu , Chaozhuo Li , Rui Ha , Zejian Chen , Litian Zhang , Zheng Liu , Lirong Qiu , Zaisheng Ye

We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success…

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

Machine Learning · Computer Science 2024-08-21 Luxi He , Mengzhou Xia , Peter Henderson

Static analysis plays a crucial role in software vulnerability detection, yet faces a persistent precision-scalability tradeoff. In large codebases like the Linux kernel, traditional static analysis tools often generate excessive false…

Software Engineering · Computer Science 2025-06-03 Haonan Li , Hang Zhang , Kexin Pei , Zhiyun Qian

The rapid advancement of large language models (LLMs) has led to significant improvements in their capabilities, but also to increased concerns about their alignment with human values and intentions. Current alignment strategies, including…

Computation and Language · Computer Science 2025-01-10 Hantao Lou , Jiaming Ji , Kaile Wang , Yaodong Yang

Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecessary exploration that wastes computation and can even…

Machine Learning · Computer Science 2026-05-12 Xinyan Wang , Xiaogeng Liu , Chaowei Xiao

Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…

Artificial Intelligence · Computer Science 2026-01-23 Manish Bhatt

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou

Many jailbreak attacks on large language models (LLMs) rely on a common objective: making the model respond with the prefix ``Sure, here is (harmful request)''. While straightforward, this objective has two limitations: limited control over…

Machine Learning · Computer Science 2025-12-30 Sicheng Zhu , Brandon Amos , Yuandong Tian , Chuan Guo , Ivan Evtimov

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Computation and Language · Computer Science 2024-03-05 Yue Deng , Wenxuan Zhang , Sinno Jialin Pan , Lidong Bing

Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies…

Cryptography and Security · Computer Science 2025-01-03 Johan Wahréus , Ahmed Mohamed Hussain , Panos Papadimitratos

Despite their remarkable success, large language models (LLMs) have shown limited ability on safety-critical code tasks such as vulnerability detection. Typically, static analysis (SA) tools, like CodeQL, CodeGuru Security, etc., are used…

Cryptography and Security · Computer Science 2025-09-15 Ira Ceka , Feitong Qiao , Anik Dey , Aastha Valecha , Gail Kaiser , Baishakhi Ray

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy…

Computation and Language · Computer Science 2025-12-05 Lang Xiong , Nishant Bhargava , Jianhang Hong , Jeremy Chang , Haihao Liu , Vasu Sharma , Kevin Zhu

Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, finetuning-based ones that compromise LLMs' safety alignment…

Cryptography and Security · Computer Science 2025-11-27 Zhixin Xie , Xurui Song , Jun Luo

The prevalence of Large Language Models (LLMs) for generating multilingual text and source code has only increased the imperative for machine-generated content detectors to be accurate and efficient across domains. Current detectors,…

Computation and Language · Computer Science 2025-10-23 Shriyansh Agrawal , Aidan Lau , Sanyam Shah , Ahan M R , Kevin Zhu , Sunishchal Dev , Vasu Sharma

Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such…

Computation and Language · Computer Science 2024-05-08 Hongyu Cai , Arjun Arunasalam , Leo Y. Lin , Antonio Bianchi , Z. Berkay Celik