English
Related papers

Related papers: Baseline Defenses for Adversarial Attacks Against …

200 papers

Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Among these attacks, adversarial…

Computation and Language · Computer Science 2024-06-11 Duy C. Hoang , Quang H. Nguyen , Saurav Manchanda , MinLong Peng , Kok-Seng Wong , Khoa D. Doan

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Cryptography and Security · Computer Science 2026-01-26 Xianya Fang , Xianying Luo , Yadong Wang , Xiang Chen , Yu Tian , Zequn Sun , Rui Liu , Jun Fang , Naiqiang Tan , Yuanning Cui , Sheng-Jun Huang

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can…

Cryptography and Security · Computer Science 2025-02-19 Xiaoqun Liu , Jiacheng Liang , Luoxi Tang , Muchao Ye , Weicheng Ma , Zhaohan Xi

The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditional false content, LLM-generated misinformation can be…

Information Retrieval · Computer Science 2025-07-09 Shuliang Liu , Hongyi Liu , Aiwei Liu , Bingchen Duan , Qi Zheng , Yibo Yan , He Geng , Peijie Jiang , Jia Liu , Xuming Hu

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

Computation and Language · Computer Science 2025-07-25 Xuandong Zhao , Xianjun Yang , Tianyu Pang , Chao Du , Lei Li , Yu-Xiang Wang , William Yang Wang

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

Modern large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities for coding tasks including writing and reasoning about code. They improve upon previous neural network models of code, such as code2seq or…

Machine Learning · Computer Science 2023-11-23 Chi Zhang , Zifan Wang , Ravi Mangal , Matt Fredrikson , Limin Jia , Corina Pasareanu

The emergence of vision-language-action models (VLAs) for end-to-end control is reshaping the field of robotics by enabling the fusion of multimodal sensory inputs at the billion-parameter scale. The capabilities of VLAs stem primarily from…

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

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Cryptography and Security · Computer Science 2025-10-21 Zhengyue Zhao , Yingzi Ma , Somesh Jha , Marco Pavone , Patrick McDaniel , Chaowei Xiao

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Multiagent Systems · Computer Science 2025-10-10 Rana Muhammad Shahroz Khan , Zhen Tan , Sukwon Yun , Charles Fleming , Tianlong Chen

The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation…

Computation and Language · Computer Science 2024-05-28 Chak Tou Leong , Yi Cheng , Kaishuai Xu , Jian Wang , Hanlin Wang , Wenjie Li

With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial…

Computation and Language · Computer Science 2026-01-23 Yuan Gao , Zhigang Liu , Xinyu Yao , Bo Chen , Xiaobing Zhao

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Artificial Intelligence · Computer Science 2025-08-26 Chongwen Zhao , Zhihao Dou , Kaizhu Huang

Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent…

Cryptography and Security · Computer Science 2024-11-13 Yulong Yang , Haoran Fan , Chenhao Lin , Qian Li , Zhengyu Zhao , Chao Shen , Xiaohong Guan

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…

Computation and Language · Computer Science 2025-04-15 Shaoqing Zhang , Zhuosheng Zhang , Kehai Chen , Rongxiang Weng , Muyun Yang , Tiejun Zhao , Min Zhang

Jailbreak attacks against large language models (LLMs) aim to induce harmful behaviors in LLMs through carefully crafted adversarial prompts. To mitigate attacks, one way is to perform adversarial training (AT)-based alignment, i.e.,…

Machine Learning · Computer Science 2026-02-03 Shaopeng Fu , Liang Ding , Jingfeng Zhang , Di Wang

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen

Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…

Artificial Intelligence · Computer Science 2025-02-04 Robin Staab , Mark Vero , Mislav Balunović , Martin Vechev

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…

Cryptography and Security · Computer Science 2026-03-31 Bhavuk Jain , Sercan Ö. Arık , Hardeo K. Thakur