2,077+ academic papers on AI security, attacks, and defenses
Showing 441–460 of 522 papers
Clear filtersTing Li, Yang Yang, Yipeng Yu +3 more
Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A...
Michael Schlichtkrull
When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous...
Vasilije Stambolic, Aritra Dhar, Lukas Cavigelli
Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the...
Zonghuan Xu, Jiayu Li, Yunhan Zhao +3 more
Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly...
Ming Tan, Wei Li, Hu Tao +4 more
Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks...
Guan-Yan Yang, Tzu-Yu Cheng, Ya-Wen Teng +2 more
The integration of Large Language Models (LLMs) into computer applications has introduced transformative capabilities but also significant security...
Wentian Zhu, Zhen Xiang, Wei Niu +1 more
Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the...
Yutao Wu, Xiao Liu, Yinghui Li +5 more
Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge bases,...
Mengyao Zhao, Kaixuan Li, Lyuye Zhang +4 more
Recent advances in Large Language Models (LLMs) have brought remarkable progress in code understanding and reasoning, creating new opportunities and...
Yue Deng, Francisco Santos, Pang-Ning Tan +1 more
Deep learning based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of...
Ruizhe Zhu
The widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt...
Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou +4 more
AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a...
Yifan Zhu, Lijia Yu, Xiao-Shan Gao
In recent years, data poisoning attacks have been increasingly designed to appear harmless and even beneficial, often with the intention of verifying...
Milad Nasr, Nicholas Carlini, Chawin Sitawarin +11 more
How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an...
Ragib Amin Nihal, Rui Wen, Kazuhiro Nakadai +1 more
Large language models (LLMs) remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints...
Muxi Diao, Yutao Mou, Keqing He +6 more
The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on...
Stanisław Pawlak, Jan Dubiński, Daniel Marczak +1 more
Model merging (MM) recently emerged as an effective method for combining large deep learning models. However, it poses significant security risks....
Kazuki Egashira, Robin Staab, Thibaud Gloaguen +2 more
Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of large language models...
Weisen Jiang, Sinno Jialin Pan
This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We...
Renhua Ding, Xiao Yang, Zhengwei Fang +3 more
Large vision-language models (LVLMs) enable autonomous mobile agents to operate smartphone user interfaces, yet vulnerabilities in their perception...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert