English
Related papers

Related papers: Can Reinforcement Learning Unlock the Hidden Dange…

200 papers

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…

Machine Learning · Computer Science 2025-03-06 Erfan Entezami , Ali Naseh

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

Large Language Models (LLMs) have showcased remarkable capabilities in following human instructions. However, recent studies have raised concerns about the robustness of LLMs when prompted with instructions combining textual adversarial…

Computation and Language · Computer Science 2024-02-27 Yuansen Zhang , Xiao Wang , Zhiheng Xi , Han Xia , Tao Gui , Qi Zhang , Xuanjing Huang

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…

Machine Learning · Computer Science 2026-02-17 Jing-Cheng Pang , Liang Lu , Xian Tang , Kun Jiang , Sijie Wu , Kai Zhang , Xubin Li

Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can…

Machine Learning · Computer Science 2026-01-05 Samuel Nathanson , Rebecca Williams , Cynthia Matuszek

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…

Machine Learning · Computer Science 2025-09-22 Maithili Joshi , Palash Nandi , Tanmoy Chakraborty

Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standardized evaluation,…

Machine Learning · Computer Science 2025-02-24 Leo Schwinn , Yan Scholten , Tom Wollschläger , Sophie Xhonneux , Stephen Casper , Stephan Günnemann , Gauthier Gidel

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Cryptography and Security · Computer Science 2024-04-15 Tianyu Zhang , Zixuan Zhao , Jiaqi Huang , Jingyu Hua , Sheng Zhong

Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…

Computation and Language · Computer Science 2020-04-24 Chen Zhu , Yu Cheng , Zhe Gan , Siqi Sun , Tom Goldstein , Jingjing Liu

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Computation and Language · Computer Science 2025-06-12 Yuxin Jiang

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models…

Computation and Language · Computer Science 2026-02-10 Thilo Hagendorff , Erik Derner , Nuria Oliver

The recent growth in the use of Large Language Models has made them vulnerable to sophisticated adversarial assaults, manipulative prompts, and encoded malicious inputs. Existing countermeasures frequently necessitate retraining models,…

Computation and Language · Computer Science 2026-03-10 Sheikh Samit Muhaimin , Spyridon Mastorakis

Large Language Models (LLMs) are now widely used in various applications, making it crucial to align their ethical standards with human values. However, recent jail-breaking methods demonstrate that this alignment can be undermined using…

Cryptography and Security · Computer Science 2023-12-11 Zhuo Zhang , Guangyu Shen , Guanhong Tao , Siyuan Cheng , Xiangyu Zhang

Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…

Cryptography and Security · Computer Science 2025-10-27 Xingwei Zhong , Kar Wai Fok , Vrizlynn L. L. Thing

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the…

Cryptography and Security · Computer Science 2024-03-05 Daoyuan Wu , Shuai Wang , Yang Liu , Ning Liu

As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…

Cryptography and Security · Computer Science 2025-11-19 Hajun Kim , Hyunsik Na , Daeseon Choi

Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which…

Computation and Language · Computer Science 2024-06-06 Timon Ziegenbein , Gabriella Skitalinskaya , Alireza Bayat Makou , Henning Wachsmuth

Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and alignment choices. While pretraining encourages models to exploit all available…

Software Engineering · Computer Science 2025-12-25 Oussama Ben Sghaier , Kevin Delcourt , Houari Sahraoui

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…

Cryptography and Security · Computer Science 2024-12-23 Hongyi Li , Jiawei Ye , Jie Wu , Tianjie Yan , Chu Wang , Zhixin Li