English
Related papers

Related papers: Turning Logic Against Itself : Probing Model Defen…

200 papers

The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained…

Computation and Language · Computer Science 2021-04-19 Xiang Gao , Yizhe Zhang , Michel Galley , Bill Dolan

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…

Computation and Language · Computer Science 2024-03-28 Abhinav Rao , Sachin Vashistha , Atharva Naik , Somak Aditya , Monojit Choudhury

The development of Long-CoT reasoning has advanced LLM performance across various tasks, including language understanding, complex problem solving, and code generation. This paradigm enables models to generate intermediate reasoning steps,…

Computation and Language · Computer Science 2025-09-05 Yanbo Wang , Yongcan Yu , Jian Liang , Ran He

Deep neural networks have been proven to be vulnerable to adversarial examples and various methods have been proposed to defend against adversarial attacks for natural language processing tasks. However, previous defense methods have…

Machine Learning · Computer Science 2024-03-01 Fangyuan Zhang , Huichi Zhou , Shuangjiao Li , Hongtao Wang

Large language models (LLMs) are increasingly used for causal and counterfactual reasoning, yet their reliability in real-world policy evaluation remains underexplored. We construct a benchmark of 40 empirical policy evaluation cases drawn…

Artificial Intelligence · Computer Science 2026-05-29 Yanjie He

Defending against jailbreak attacks is crucial for the safe deployment of Large Language Models (LLMs). Recent research has attempted to improve safety by training models to reason over safety rules before responding. However, a key issue…

Artificial Intelligence · Computer Science 2026-01-08 Di Wu , Yanyan Zhao , Xin Lu , Mingzhe Li , Bing Qin

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…

Computation and Language · Computer Science 2025-11-05 Berk Atil , Rebecca J. Passonneau , Fred Morstatter

Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Research towards pluralism alignment has many efforts in enhancing the learning of large…

Computation and Language · Computer Science 2026-04-21 Ying Su , Mingen Zheng , Weili Diao , Haoran Li

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting. However, CoT can be biased by users' instruction. In this work, we study the reasoning robustness of LLMs to…

Computation and Language · Computer Science 2024-11-11 Esther Gan , Yiran Zhao , Liying Cheng , Yancan Mao , Anirudh Goyal , Kenji Kawaguchi , Min-Yen Kan , Michael Shieh

While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks. We point out a pivotal factor contributing to the success of…

Computation and Language · Computer Science 2024-06-13 Zhexin Zhang , Junxiao Yang , Pei Ke , Fei Mi , Hongning Wang , Minlie Huang

In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to…

Cryptography and Security · Computer Science 2026-05-27 Xuan Luo , Yue Wang , Geng Tu , Jing Li , Ruifeng Xu

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. However, they are still limited due to redundant attack…

Computation and Language · Computer Science 2022-10-19 Lan Jiang , Hao Zhou , Yankai Lin , Peng Li , Jie Zhou , Rui Jiang

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer.…

Cryptography and Security · Computer Science 2026-05-13 Xinkai Zhang , Zhipeng Wei , Huanli Gong , Jing Ting Zheng , Yuchen Zhang , Yue Dong , N. Benjamin Erichson

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Computation and Language · Computer Science 2025-11-26 Isack Lee , Haebin Seong

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

As large language models (LLMs) are increasingly deployed across diverse domains, ensuring their safety has become a critical concern. In response, studies on jailbreak attacks have been actively growing. Existing approaches typically rely…

Artificial Intelligence · Computer Science 2025-08-05 Yelim Ahn , Jaejin Lee

As chain-of-thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through…

Artificial Intelligence · Computer Science 2026-03-03 Kyle Cox , Darius Kianersi , Adrià Garriga-Alonso

Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and…

Computation and Language · Computer Science 2025-02-19 Bangxin Li , Hengrui Xing , Cong Tian , Chao Huang , Jin Qian , Huangqing Xiao , Linfeng Feng

Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of…

Cryptography and Security · Computer Science 2025-06-23 Biao Yi , Tiansheng Huang , Sishuo Chen , Tong Li , Zheli Liu , Zhixuan Chu , Yiming Li

Multimodal LLMs (MLLMs) with a great ability of text and image understanding have received great attention. To achieve better reasoning with MLLMs, Chain-of-Thought (CoT) reasoning has been widely explored, which further promotes MLLMs'…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Zefeng Wang , Zhen Han , Shuo Chen , Fan Xue , Zifeng Ding , Xun Xiao , Volker Tresp , Philip Torr , Jindong Gu