English
Related papers

Related papers: Attention Misses Visual Risk: Risk-Adaptive Steeri…

200 papers

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Machine Learning · Computer Science 2026-01-07 Tuc Nguyen , Thai Le

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Cryptography and Security · Computer Science 2025-11-18 Xuankun Rong , Wenke Huang , Tingfeng Wang , Daiguo Zhou , Bo Du , Mang Ye

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 In Chong Choi , Jiacheng Zhang , Feng Liu , Yiliao Song

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

Artificial Intelligence · Computer Science 2026-04-03 Hamin Koo , Minseon Kim , Jaehyung Kim

Deep learning models often achieve expert-level accuracy in medical image classification but suffer from a critical flaw: semantic incoherence. These high-confidence mistakes that are semantically incoherent (e.g., classifying a malignant…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Abolfazl Mohammadi-Seif , Ricardo Baeza-Yates

In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received strangely less attention than obstacle number or density. Existing methods typically extract purely geometric features from…

Robotics · Computer Science 2026-05-15 Hong Hong , Feiyu Liao , Yongheng Liang , Boning Zhang , Haitao Wang , Hejun Wu

Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much high dimension, which brings huge computational costs when…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Wei Xingxing , Wang Songping , Yan Huanqian

In Machine Learning (ML)-enabled autonomous systems (MLASs), it is essential to identify the hazard boundary of ML Components (MLCs) in the MLAS under analysis. Given that such boundary captures the conditions in terms of MLC behavior and…

Software Engineering · Computer Science 2023-10-17 Sepehr Sharifi , Donghwan Shin , Lionel C. Briand , Nathan Aschbacher

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the…

Machine Learning · Computer Science 2025-10-10 Huahui Yi , Kun Wang , Qiankun Li , Miao Yu , Liang Lin , Gongli Xi , Hao Wu , Xuming Hu , Kang Li , Yang Liu

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Machine Learning · Computer Science 2024-02-06 Xinglong Zhang , Yaoqian Peng , Biao Luo , Wei Pan , Xin Xu , Haibin Xie

Driver Monitoring Systems (DMSs) are crucial for safe hand-over actions in Level-2+ self-driving vehicles. State-of-the-art DMSs leverage multiple sensors mounted at different locations to monitor the driver and the vehicle's interior scene…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Yiming Ma , Victor Sanchez , Soodeh Nikan , Devesh Upadhyay , Bhushan Atote , Tanaya Guha

We study dynamic pricing of a product with an unknown demand distribution over a finite horizon. Departing from the standard no-regret learning environment in which prices can be adjusted at any time, we restrict price changes to…

Machine Learning · Computer Science 2025-12-16 Parshan Pakiman , Boxiao Chen , Selvaprabu Nadarajah , Stefanus Jasin

Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large human-annotated datasets and static red-teaming benchmarks that are costly, difficult to scale,…

Computation and Language · Computer Science 2026-03-10 Punyajoy Saha , Sudipta Halder , Debjyoti Mondal , Subhadarshi Panda

Foundation MLIPs demonstrate broad applicability across diverse material systems and have emerged as a powerful and transformative paradigm in chemical and computational materials science. Equivariant MLIPs achieve state-of-the-art accuracy…

Machine Learning · Computer Science 2026-03-09 Yuanchang Zhou , Siyu Hu , Xiangyu Zhang , Hongyu Wang , Guangming Tan , Weile Jia

Multimodal embedding models, built upon causal Vision Language Models (VLMs), have shown promise in various tasks. However, current approaches face three key limitations: the use of causal attention in VLM backbones is suboptimal for…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Haonan Chen , Hong Liu , Yuping Luo , Liang Wang , Nan Yang , Furu Wei , Zhicheng Dou

Obtaining large-scale labeled object detection dataset can be costly and time-consuming, as it involves annotating images with bounding boxes and class labels. Thus, some specialized active learning methods have been proposed to reduce the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Yi-Syuan Liou , Tsung-Han Wu , Jia-Fong Yeh , Wen-Chin Chen , Winston H. Hsu

Past few years have witnessed a growing recognition of intelligent techniques for the construction of efficient and reliable intrusion detection systems. Due to increasing incidents of cyber attacks, building effective intrusion detection…

Artificial Intelligence · Computer Science 2007-05-23 Srinivas Mukkamala , Andrew H. Sung , Ajith Abraham , Vitorino Ramos

Autonomous Systems (AS) are increasingly proposed, or used, in Safety Critical (SC) applications. Many such systems make use of sophisticated sensor suites and processing to provide scene understanding which informs the AS' decision-making.…

Systems and Control · Electrical Eng. & Systems 2022-08-19 John Molloy , John McDermid

Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater vulnerability than their text-only LLM backbones. To…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Xiaohan Zou , Jian Kang , George Kesidis , Lu Lin

Autonomous driving decision-making at unsignalized intersections is highly challenging due to complex dynamic interactions and high conflict risks. To achieve proactive safety control, this paper proposes a deep reinforcement learning (DRL)…

Artificial Intelligence · Computer Science 2025-10-15 Chengyang Dong , Nan Guo