AI Threat Alert indexes 4,319+ 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 501–520 of 4,319 papers
Xianhui Zhang, Jian Yu, Chengyu Xie +6 more
Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to...
Xianhui Zhang, Jian Yu, Chengyu Xie +6 more
Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to...
Federico Torrielli, Gianluca Barmina, Andrea Blasi Núñez +4 more
Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is...
Hongxu Su, Jianzhu Yao, Xuechao Wang +1 more
Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into...
Jesson Wang, Shawn Li, Wei Yang +4 more
Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely...
Haoran Ou, Gelei Deng, Xuanye Zhang +3 more
As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent...
Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu +2 more
Fine-tuning-as-a-service lets users adapt a safety-aligned language model to their own data, but it also creates a harmful fine-tuning attack...
Omar Sheta, Rinku Deuja, Hadi Masoudi +1 more
Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns...
Zonghao Ying, Xiangfan Wu, Bo Yang +5 more
Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user...
Bravish Ghosh
Multi-agent LLM systems are increasingly structured like organizations, with roles, critics and shared memory, yet they are evaluated on tasks that...
Zonghua Gu, Zeyu Gao, Amin Saremi +1 more
Adversarial machine learning has focused mainly on integrity, but availability is an increasingly consequential complement. Latency attacks (also...
Minh Nhat Le, Nisarga Gondi, Yibo Peng +4 more
Large language models (LLMs) increasingly power agents that access sensitive information, use external tools, and modify software repositories....
Michael Lee, Zhipeng Wei, Yue Dong +1 more
Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large...
Sujin Chen, Lijun Li, Xuhong Wang +1 more
While LLM-based attackers exhibit growing proficiency in vulnerability exploitation, most existing cybersecurity benchmarks suffer from single-stage...
Mark Russinovich
Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...
Lijie Zheng, Ji He, Ying Wang +2 more
Provenance-based intrusion detection systems (PIDSs) identify suspicious activity in audit streams, but their outputs remain difficult to turn into...
Rikhiya Ghosh, Himanshu Kumar, Sriram Venkatapathy +3 more
In regulated industries like consumer finance, seemingly harmless user queries can exploit large language model vulnerabilities, triggering safety...
Pedro Beltrán-López, Enrique Tomás Martínez Beltrán, Pantaleone Nespoli +2 more
Decentralized Federated Learning (DFL) eliminates the central aggregation server, reducing the single point of observation that traditional defenses...
Aadith Sukumar, Isha Singh, Devershika Mohane +4 more
Distributed Denial of Service attacks are a growing threat to network infrastructure, and new techniques, including the use of generative AI, make...
Jie Zhang, Andrei Baroian, Jan N. van Rijn +2 more
Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this...
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 4,319+ 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