English
Related papers

Related papers: Estimating Worst-Case Frontier Risks of Open-Weigh…

200 papers

Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly vulnerable because they process both text and images, creating broader attack surfaces.…

Computation and Language · Computer Science 2026-02-23 Mirae Kim , Seonghun Jeong , Youngjun Kwak

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Yubo Cui , Xianchao Guan , Zijun Xiong , Zheng Zhang

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Yunqing Zhao , Tianyu Pang , Chao Du , Xiao Yang , Chongxuan Li , Ngai-Man Cheung , Min Lin

Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely large enough to observe the failures that matter. Jones et al. (2025) address this by…

Machine Learning · Computer Science 2026-05-18 Will Schwarzer , Scott Niekum

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Security concerns related to Large Language Models (LLMs) have been extensively explored, yet the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain insufficiently studied.…

Cryptography and Security · Computer Science 2024-08-22 Xijie Huang , Xinyuan Wang , Hantao Zhang , Yinghao Zhu , Jiawen Xi , Jingkun An , Hao Wang , Hao Liang , Chengwei Pan

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering…

Large Language Models (LLMs) enhanced with external contexts, such as through retrieval-augmented generation (RAG), often face challenges in handling imperfect evidence. They tend to over-rely on external knowledge, making them vulnerable…

Computation and Language · Computer Science 2025-02-25 Shenglai Zeng , Pengfei He , Kai Guo , Tianqi Zheng , Hanqing Lu , Yue Xing , Hui Liu

With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased…

Cryptography and Security · Computer Science 2024-12-17 Haoran Li , Yulin Chen , Zihao Zheng , Qi Hu , Chunkit Chan , Heshan Liu , Yangqiu Song

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

Cryptography and Security · Computer Science 2026-01-13 Xin Wang , Yunhao Chen , Juncheng Li , Yixu Wang , Yang Yao , Tianle Gu , Jie Li , Yan Teng , Yingchun Wang , Xia Hu

Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the first comprehensive evaluation of 10…

Cryptography and Security · Computer Science 2025-10-27 Divyanshu Kumar , Nitin Aravind Birur , Tanay Baswa , Sahil Agarwal , Prashanth Harshangi

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche…

Machine Learning · Computer Science 2025-08-18 Brendan R. Hogan , Will Brown , Adel Boyarsky , Anderson Schneider , Yuriy Nevmyvaka

Recent research has demonstrated the potential of Large Language Models (LLMs) for autonomous penetration testing, particularly when using cloud-based restricted-weight models. However, reliance on such models introduces security, privacy,…

Cryptography and Security · Computer Science 2026-05-01 Benjamin Probst , Andreas Happe , Jürgen Cito

Recent advancements in artificial intelligence have enabled processing of larger inputs, leading everyday software developers to increasingly rely on chat-based large language models (LLMs) like GPT-3.5 and GPT-4 to detect vulnerabilities…

Software Engineering · Computer Science 2025-02-12 Francesco Sovrano , Adam Bauer , Alberto Bacchelli

Large Language Models (LLMs) have become an integral part of our daily lives. However, they impose certain risks, including those that can harm individuals' privacy, perpetuate biases and spread misinformation. These risks highlight the…

Software Engineering · Computer Science 2025-01-30 Aitor Arrieta , Miriam Ugarte , Pablo Valle , José Antonio Parejo , Sergio Segura

Recent studies have shown that Machine Learning (ML) models can exhibit bias in real-world scenarios, posing significant challenges in ethically sensitive domains such as healthcare. Such bias can negatively affect model fairness, model…

Machine Learning · Computer Science 2025-09-05 Junyu Yan , Feng Chen , Yuyang Xue , Yuning Du , Konstantinos Vilouras , Sotirios A. Tsaftaris , Steven McDonagh

Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized optimization expertise. Although Large Language Models (LLMs)…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-12 Ali Tehrani , Yahya Emara , Essam Wissam , Wojciech Paluch , Waleed Atallah , Łukasz Dudziak , Mohamed S. Abdelfattah

Pre-trained foundation models (FMs), with extensive number of neurons, are key to advancing next-generation intelligence services, where personalizing these models requires massive amount of task-specific data and computational resources.…

Systems and Control · Electrical Eng. & Systems 2024-07-04 Zixin Wang , Yong Zhou , Yuanming Shi , Khaled. B. Letaief

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

Artificial Intelligence · Computer Science 2026-02-03 Abhishek Mishra , Mugilan Arulvanan , Reshma Ashok , Polina Petrova , Deepesh Suranjandass , Donnie Winkelmann

Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve reliability at the system level or address specific issues…

Software Engineering · Computer Science 2026-05-07 Lingzhe Zhang , Tong Jia , Yunpeng Zhai , Liancheng Fang , Kening Zheng , Hongyi Liu , Xiaosong Huang , Philip S. Yu , Ying Li