English
Related papers

Related papers: ExplainableGuard: Interpretable Adversarial Defens…

200 papers

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

Cryptography and Security · Computer Science 2024-12-11 Bocheng Chen , Hanqing Guo , Qiben Yan

The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to ethically align LLMs, these are often fragile and can be…

Computation and Language · Computer Science 2024-10-11 Zichuan Liu , Zefan Wang , Linjie Xu , Jinyu Wang , Lei Song , Tianchun Wang , Chunlin Chen , Wei Cheng , Jiang Bian

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks by engaging in extended reasoning before producing final answers. Beyond improving abilities, these detailed reasoning traces also create a new…

Computation and Language · Computer Science 2026-01-08 Shu Yang , Junchao Wu , Xilin Gong , Xuansheng Wu , Derek Wong , Ninghao Liu , Di Wang

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Artificial Intelligence · Computer Science 2025-04-02 Yu Cui , Bryan Hooi , Yujun Cai , Yiwei Wang

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Computation and Language · Computer Science 2025-11-04 Sriram Balasubramanian , Samyadeep Basu , Soheil Feizi

Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks. However, the adversarial examples generated by many mainstream…

Computation and Language · Computer Science 2023-11-21 Zimu Wang , Wei Wang , Qi Chen , Qiufeng Wang , Anh Nguyen

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Cryptography and Security · Computer Science 2024-02-13 Raha Moraffah , Shubh Khandelwal , Amrita Bhattacharjee , Huan Liu

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Computation and Language · Computer Science 2025-06-13 Jaechul Roh , Varun Gandhi , Shivani Anilkumar , Arin Garg

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning…

Computation and Language · Computer Science 2025-02-19 Huawei Lin , Yingjie Lao , Tong Geng , Tan Yu , Weijie Zhao

Large Language Models (LLMs) are increasingly deployed in real-world applications that demand complex reasoning. To track progress, robust benchmarks are required to evaluate their capabilities beyond superficial pattern recognition.…

Computation and Language · Computer Science 2025-06-03 Wenye Lin , Jonathan Roberts , Yunhan Yang , Samuel Albanie , Zongqing Lu , Kai Han

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Computation and Language · Computer Science 2025-10-27 Bushra Sabir , Yansong Gao , Alsharif Abuadbba , M. Ali Babar

Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…

Computation and Language · Computer Science 2025-12-30 Samuel Simko , Mrinmaya Sachan , Bernhard Schölkopf , Zhijing Jin

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…

Computation and Language · Computer Science 2025-10-15 Divij Handa , Zehua Zhang , Amir Saeidi , Shrinidhi Kumbhar , Md Nayem Uddin , Aswin RRV , Chitta Baral

Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these…

Computation and Language · Computer Science 2025-05-01 Canaan Yung , Hadi Mohaghegh Dolatabadi , Sarah Erfani , Christopher Leckie

Although social media platforms are a prominent arena for users to engage in interpersonal discussions and express opinions, the facade and anonymity offered by social media may allow users to spew hate speech and offensive content. Given…

Computation and Language · Computer Science 2024-05-09 Ayushi Nirmal , Amrita Bhattacharjee , Paras Sheth , Huan Liu

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Computation and Language · Computer Science 2024-05-03 Mansi Phute , Alec Helbling , Matthew Hull , ShengYun Peng , Sebastian Szyller , Cory Cornelius , Duen Horng Chau

Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the mid-to-late steps of their reasoning processes. Current…

Computation and Language · Computer Science 2026-05-07 Yuquan Wang , Mi Zhang , Yining Wang , Geng Hong , Mi Wen , Xiaoyu You , Min Yang

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety…

Computation and Language · Computer Science 2025-10-16 Changyi Li , Jiayi Wang , Xudong Pan , Geng Hong , Min Yang

Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-11-20 Eunkyu Park , Wesley Hanwen Deng , Vasudha Varadarajan , Mingxi Yan , Gunhee Kim , Maarten Sap , Motahhare Eslami

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in…

Computation and Language · Computer Science 2024-09-16 Zeyu Yang , Zhao Meng , Xiaochen Zheng , Roger Wattenhofer