2,529+ academic papers on AI security, attacks, and defenses
Showing 101–120 of 2,529 papers
Karima Makhlouf, Lamiaa Basyoni, Syed Khaderi +4 more
Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While...
Ji Guo, Xiaolong Qin, Cencen Liu +3 more
Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as...
Mingyu Luo, Zihan Zhang, Zesen Liu +7 more
Bring-Your-Own-Key (BYOK) agent architectures let users route LLM traffic through third-party relays, creating a critical integrity gap: a malicious...
Wenwei Zhao, Xiaowen Li, Yao Liu +1 more
Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients upload manipulated updates to degrade the performance of the...
Debeshee Das, Julien Piet, Darya Kaviani +3 more
Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We...
Sadia Asif, Mohammad Mohammadi Amiri
Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable...
Jiajia Li, Xiaoyu Wen, Zhongtian Ma +3 more
The growing capabilities of large language models (LLMs) have driven their widespread deployment across diverse domains, even in potentially...
George Fatouros, Georgios Makridis, John Soldatos +18 more
European financial institutions face mounting regulatory pressure while their security operations centres remain constrained not by data or staffing...
Mohd Ruhul Ameen, Md Takrim Ul Alam, Akif Islam
Static Application Security Testing tools help developers find security vulnerabilities before release, but they often produce many false positives....
Zhiyang Dai, Yansong Gao, Boyu Kuang +5 more
Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible,...
Huining Cui, Wei Liu
Retrieval-augmented generation (RAG) improves factual grounding by conditioning large language models on retrieved evidence, but it also opens a...
Yanting Wang, Chenlong Yin, Ying Chen +1 more
Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as...
Prashant Kulkarni
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where...
Bowen Sun, Chaozhuo Li, Yaodong Yang +2 more
Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a...
Jona te Lintelo, Lichao Wu, Marina Krček +2 more
Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation. However,...
Xiaokun Luan, Yihao Zhang, Pengcheng Su +2 more
Large Language Model (LLM) watermarking is crucial for establishing the provenance of machine-generated text, but most existing methods rely on a...
Han Liu, Shanghao Shi, Yevgeniy Vorobeychik +2 more
Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved...
Luyao Xu, Xiang Chen
Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems,...
Zehui Tang, Yuchen Liu, Feihu Huang
Federated learning (FL) is a popular distributed learning paradigm in machine learning, which enables multiple clients to collaboratively train...
Zi Li, Tian Zhou, Wenze Li +3 more
Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local...
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