AI Threat Alert indexes 3,771+ peer-reviewed and preprint papers on AI/ML security — covering adversarial attacks, model defenses, red-teaming benchmarks, surveys, and security tooling. Papers are sourced from arXiv, classified by type and by relevance to real-world threats, and cross-referenced with the CVEs and incidents they relate to.
Showing 1301–1320 of 1,458 papers
Clear filtersYushi Yang, Shreyansh Padarha, Andrew Lee +1 more
Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common...
Xinkai Wang, Beibei Li, Zerui Shao +3 more
Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual...
Giulia Giusti
The concept of linearity plays a central role in both mathematics and computer science, with distinct yet complementary meanings. In mathematics,...
Elias Hossain, Swayamjit Saha, Somshubhra Roy +1 more
Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference...
Masahiro Kaneko, Zeerak Talat, Timothy Baldwin
Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the...
Masahiro Kaneko, Timothy Baldwin
Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property...
Mansi Phute, Matthew Hull, Haoran Wang +6 more
Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial...
Amirkia Rafiei Oskooei, Mehmet S. Aktas
The proficiency of Large Language Models (LLMs) in processing structured data and adhering to syntactic rules is a capability that drives their...
Jie Zhang, Meng Ding, Yang Liu +2 more
We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural...
Asmita Mohanty, Gezheng Kang, Lei Gao +1 more
Large Language Models (LLMs) have demonstrated strong performance across diverse tasks, but fine-tuning them typically relies on cloud-based,...
Alireza Heshmati, Saman Soleimani Roudi, Sajjad Amini +2 more
Existing adversarial attacks often neglect perturbation sparsity, limiting their ability to model structural changes and to explain how deep neural...
Dimitris Stefanopoulos, Andreas Voskou
This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery...
Sarah Egler, John Schulman, Nicholas Carlini
Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that...
Owais Makroo, Siva Rajesh Kasa, Sumegh Roychowdhury +4 more
Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a...
Shuang Liang, Zhihao Xu, Jialing Tao +2 more
Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To...
Deyue Zhang, Dongdong Yang, Junjie Mu +6 more
Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal...
Evangelos Lamprou, Julian Dai, Grigoris Ntousakis +2 more
Software supply-chain attacks are an important and ongoing concern in the open source software ecosystem. These attacks maintain the standard...
Xiaoyu Xue, Yuni Lai, Chenxi Huang +4 more
The emergence of graph foundation models (GFMs), particularly those incorporating language models (LMs), has revolutionized graph learning and...
Andrew Zhao, Reshmi Ghosh, Vitor Carvalho +4 more
Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots,...
Yingguang Yang, Xianghua Zeng, Qi Wu +5 more
Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has...
AI security research studies how AI and machine-learning systems can be attacked and defended — covering adversarial examples, prompt injection, model poisoning, training-data extraction, and the mitigations against them. AI Threat Alert curates this research from academic sources so security teams can track the threats behind emerging AI risks.
AI Threat Alert indexes 3,771+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Papers are sourced from arXiv, then classified by type and by relevance to real-world AI/ML threats, and cross-referenced with the CVEs and incidents they relate to.
Coverage spans adversarial attacks, model and system defenses, red-teaming benchmarks, literature surveys, and security tooling for LLMs, ML libraries, AI agents, and inference pipelines.
Every paper is filtered for AI security relevance and linked to the vulnerabilities, vendors, and incidents it relates to, so the research connects directly to operational threat intelligence.
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