AI Threat Alert indexes 3,023+ 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 41–60 of 759 papers
Clear filtersXuanyu Yin, Yilin Jiang, Jun Zhou +3 more
As large language models (LLMs) are increasingly deployed in user-facing systems, black-box jailbreak defense has become an important practical...
Sipeng Xie, Qianhong Wu, Hengrun Lu +4 more
Agents increasingly access large language models (LLMs) through API routers. A router terminates the client's transport-layer security session and...
Hao-Hsuan Chen
Paper A defines a time-consistent actuarial runtime that prices each side-effect-bearing action against a contractually fixed safe default and gates...
Liuyang Yao, Zhouyu Li, Junguang He +1 more
AI systems are increasingly deployed for credit assessment and investment advisory in global financial markets, yet the integrity of their inference...
Yuyang Dai, Yushun Dong
Large language models deployed as commercial APIs are vulnerable to model extraction attacks, while existing defenses either act too late or degrade...
Aman Anifer, Vignesh Kumar Kembu, Vishnu M +4 more
Large Language Models (LLMs) constitute pivotal components within the AI-dominated information technology ecosystem. To mitigate risks associated...
Achraf Hsain, Sultan Almuhammadi
Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata...
Haowei Qian
As LLM agents proliferate in prediction markets and collective decision-making, they risk a cognitive monoculture: agents built on shared foundation...
Pengfei He, Lesly Miculicich, Vishesh Sharma +5 more
Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security...
Ahmed Sharshar, Naveen Kumar Kummari, Mohsen Guizani
Continual learning (CL) models often use experience replay to reduce catastrophic forgetting, but their robustness to replay sampling interference...
Xinhai Zou, Chang Zhao, Alireza Aghabagherloo +3 more
Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently...
Yitong Zhang, Shiteng Lu, Jia Li
Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code....
Yuefang Lian, Longkun Guo, Zhongrui Zhao +5 more
Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data...
Hongzhou Rao, Zikan Dong, Yanjie Zhao +2 more
With the widespread adoption of Large Language Models (LLMs) in software engineering (SE) tasks such as code understanding, debugging, and...
Tu Lan, Chaowei Xiao
Agent skills let LLM agents reuse instructions, resources, tools, and workflows, but they also create a new place for malicious behavior to hide. A...
Omid Ahmadieh, Nima Karimian
The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent. To...
Sayedeh Leila Noorbakhsh, Hossein Khalili, Nader Sehatbakhsh
Collaborative edge-cloud inference enables resource-constrained devices to leverage large language models (LLMs) by offloading partial computation to...
Walther A. Del Orbe, John D. Hastings, Varghese Vaidyan
AI-powered code generation systems have transformed software development but introduce critical inference-time security vulnerabilities. This...
Lena S. Bolliger, Lena A. Jäger
Production LLMs receive instructions from sources with very different levels of trust, yet attend to every token with uniform architectural...
Yv Zhang, Hao Sun, Hao Fang +5 more
External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However,...
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 3,023+ 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