2,529+ academic papers on AI security, attacks, and defenses
Showing 381–400 of 440 papers
Clear filtersShuai Li, Kejiang Chen, Jun Jiang +5 more
Large Language Models (LLMs) have demonstrated remarkable capabilities, but their training requires extensive data and computational resources,...
Qiushi Wu, Yue Xiao, Dhilung Kirat +3 more
Fixing bugs in large programs is a challenging task that demands substantial time and effort. Once a bug is found, it is reported to the project...
Yibo Peng, James Song, Lei Li +6 more
Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively...
Jonghyun Park, Minhyuk Seo, Jonghyun Choi
One of the key challenges of modern AI models is ensuring that they provide helpful responses to benign queries while refusing malicious ones. But...
Xin Zhao, Xiaojun Chen, Bingshan Liu +3 more
Large language models (LLMs) with Mixture-of-Experts (MoE) architectures achieve impressive performance and efficiency by dynamically routing inputs...
Juan Ren, Mark Dras, Usman Naseem
Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs...
João A. Leite, Arnav Arora, Silvia Gargova +5 more
Large Language Models (LLMs) can generate human-like disinformation, yet their ability to personalise such content across languages and demographics...
Blazej Manczak, Eric Lin, Francisco Eiras +2 more
Large language models (LLMs) are rapidly transitioning into medical clinical use, yet their reliability under realistic, multi-turn interactions...
Lipeng He, Vasisht Duddu, N. Asokan
Chatbot providers (e.g., OpenAI) rely on tiered subscription schemes to generate revenue, offering basic models for free users, and advanced models...
Shuo Chen, Zonggen Li, Zhen Han +7 more
Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online...
Dominik Schwarz
The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking,...
Sarah Ball, Andreas Haupt
Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs. A common strategy is to fine-tune the...
Jiayu Ding, Lei Cui, Li Dong +2 more
Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex...
Mohan Zhang, Yihua Zhang, Jinghan Jia +3 more
Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative...
Shaolun Liu, Sina Marefat, Omar Tsai +4 more
GraphQL's flexible query model and nested data dependencies expose APIs to complex, context-dependent vulnerabilities that are difficult to uncover...
Zonghao Ying, Yangguang Shao, Jianle Gan +9 more
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in...
Ines Altemir Marinas, Anastasiia Kucherenko, Alexander Sternfeld +1 more
The performance of Large Language Models (LLMs) is determined by their training data. Despite the proliferation of open-weight LLMs, access to LLM...
Yongding Tao, Tian Wang, Yihong Dong +4 more
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples...
Xiaonan Si, Meilin Zhu, Simeng Qin +7 more
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and...
Debeshee Das, Luca Beurer-Kellner, Marc Fischer +1 more
The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt...
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