English
Related papers

Related papers: BarrierSteer: LLM Safety via Learning Barrier Stee…

200 papers

Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Machine Learning · Computer Science 2026-04-20 Zixuan Weng , Jinghuai Zhang , Kunlin Cai , Ying Li , Peiran Wang , Yuan Tian

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

Computation and Language · Computer Science 2026-02-17 Hanjiang Hu , Alexander Robey , Changliu Liu

In this work, we consider the problem of designing a safety filter for a nonlinear uncertain control system. Our goal is to augment an arbitrary controller with a safety filter such that the overall closed-loop system is guaranteed to stay…

Robotics · Computer Science 2022-04-11 Lukas Brunke , Siqi Zhou , Angela P. Schoellig

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Artificial Intelligence · Computer Science 2026-05-13 Xinyi Zeng , Xue Yang , Jingyuan Zhang , Huanqian Yan , Xiang Chen , Kaiwen Wei , Hankun Kang , Yu Tian

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Cryptography and Security · Computer Science 2025-09-29 Xiyu Zeng , Siyuan Liang , Liming Lu , Haotian Zhu , Enguang Liu , Jisheng Dang , Yongbin Zhou , Shuchao Pang

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even…

Computation and Language · Computer Science 2024-10-03 Amrita Bhattacharjee , Shaona Ghosh , Traian Rebedea , Christopher Parisien

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…

Computation and Language · Computer Science 2025-09-24 Lyucheng Wu , Mengru Wang , Ziwen Xu , Tri Cao , Nay Oo , Bryan Hooi , Shumin Deng

This paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The presented framework applies the CBF safety filter to the…

Computation and Language · Computer Science 2026-03-31 Yuya Miyaoka , Masaki Inoue

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…

Computation and Language · Computer Science 2026-03-03 Haolei Xu , Xinyu Mei , Yuchen Yan , Rui Zhou , Wenqi Zhang , Weiming Lu , Yueting Zhuang , Yongliang Shen

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

Artificial Intelligence · Computer Science 2025-09-25 Huizhen Shu , Xuying Li , Zhuo Li

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing…

Systems and Control · Electrical Eng. & Systems 2019-12-24 Andrew Taylor , Andrew Singletary , Yisong Yue , Aaron Ames

Large Audio-Language Models (LALMs) are becoming essential as a powerful multimodal backbone for real-world applications. However, recent studies show that audio inputs can more easily elicit harmful responses than text, exposing new risks…

Sound · Computer Science 2026-05-08 Weilin Lin , Jianze Li , Hui Xiong , Li Liu

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

Cryptography and Security · Computer Science 2024-06-26 Yi Zeng , Weiyu Sun , Tran Ngoc Huynh , Dawn Song , Bo Li , Ruoxi Jia

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Control Barrier Functions (CBFs) provide an elegant framework for constraining nonlinear control system dynamics to remain within an invariant subset of a designated safe set. However, identifying a CBF that balances performance-by…

Machine Learning · Computer Science 2024-11-05 Lakshmideepakreddy Manda , Shaoru Chen , Mahyar Fazlyab

This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems. CBFs are usually overly conservative, while guaranteeing safety. Here, we address their…

Machine Learning · Computer Science 2021-11-23 Wei Xiao , Ramin Hasani , Xiao Li , Daniela Rus

Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit instability due to their sensitivity to prompt changes, while…

Computation and Language · Computer Science 2025-07-08 Yichen Li , Zhiting Fan , Ruizhe Chen , Xiaotang Gai , Luqi Gong , Yan Zhang , Zuozhu Liu

Breaking safety constraints in control systems can lead to potential risks, resulting in unexpected costs or catastrophic damage. Nevertheless, uncertainty is ubiquitous, even among similar tasks. In this paper, we develop a novel adaptive…

Systems and Control · Electrical Eng. & Systems 2023-07-17 Shengbo Wang , Ke Li , Yin Yang , Yuting Cao , Tingwen Huang , Shiping Wen

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal
‹ Prev 1 2 3 10 Next ›