2,589+ academic papers on AI security, attacks, and defenses
Showing 1201–1220 of 1,928 papers
Clear filtersGloria Felicia, Michael Eniolade, Jinfeng He +4 more
Existing agent safety benchmarks report binary accuracy, conflating early intervention with post-mortem analysis. A detector that flags a violation...
Xiaogeng Liu, Xinyan Wang, Yechao Zhang +5 more
Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of...
Xiaoyu Xu, Minxin Du, Kun Fang +6 more
Large language models (LLMs) demonstrate impressive capabilities across diverse tasks but raise concerns about privacy, copyright, and harmful...
Mingyang Liao, Yichen Wan, shuchen wu +6 more
LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak...
Ningyuan He, Ronghong Huang, Qianqian Tang +3 more
In-context learning (ICL) has become a powerful, data-efficient paradigm for text classification using large language models. However, its robustness...
Wenhui Zhang, Huiyu Xu, Zhibo Wang +4 more
Recent advancements in multi-model AI systems have leveraged LLM routers to reduce computational cost while maintaining response quality by assigning...
Devanshu Sahoo, Manish Prasad, Vasudev Majhi +5 more
The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following...
Xiang Zheng, Yutao Wu, Hanxun Huang +5 more
Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and...
Alvi Md Ishmam, Najibul Haque Sarker, Zaber Ibn Abdul Hakim +1 more
Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to...
Arther Tian, Alex Ding, Frank Chen +2 more
Decentralized large language model inference networks require lightweight mechanisms to reward high quality outputs under heterogeneous latency and...
Jarrod Barnes
As large language models (LLMs) improve, so do their offensive applications: frontier agents now generate working exploits for under $50 in compute...
Onkar Shelar, Travis Desell
Evolutionary prompt search is a practical black-box approach for red teaming large language models (LLMs), but existing methods often collapse onto a...
Mingqiao Mo, Yunlong Tan, Hao Zhang +2 more
Large language models (LLMs) have achieved remarkable progress in code generation, yet their potential for software protection remains largely...
Xingwei Lin, Wenhao Lin, Sicong Cao +4 more
Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively...
Yizhong Ding
Webshells remain a primary foothold for attackers to compromise servers, particularly within PHP ecosystems. However, existing detection mechanisms...
Holly Trikilis, Pasindu Marasinghe, Fariza Rashid +1 more
Phishing continues to be one of the most prevalent attack vectors, making accurate classification of phishing URLs essential. Recently, large...
Mohsen Hatami, Van Tuan Pham, Hozefa Lakadawala +1 more
The increasing integration of AI agents into cyber-physical systems (CPS) introduces new security risks that extend beyond traditional cyber or...
Yuetian Chen, Kaiyuan Zhang, Yuntao Du +5 more
Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction....
Faezeh Hosseini, Mohammadali Yousefzadeh, Yadollah Yaghoobzadeh
Figurative language, particularly fixed figurative expressions (FFEs) such as idioms and proverbs, poses persistent challenges for large language...
Md Tasnim Jawad, Mingyan Xiao, Yanzhao Wu
With the widespread adoption of Large Language Models (LLMs) and increasingly stringent privacy regulations, protecting data privacy in LLMs has...
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