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 81–100 of 142 papers
Clear filtersChe Wang, Jiaming Zhang, Ziqi Zhang +6 more
The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for...
Ian Steenstra, Paola Pedrelli, Weiyan Shi +2 more
Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the...
Xingyu Shen, Tommy Duong, Xiaodong An +6 more
Age estimation systems are increasingly deployed as gatekeepers for age-restricted online content, yet their robustness to cosmetic modifications has...
Phan The Duy, Nghi Hoang Khoa, Nguyen Tran Anh Quan +3 more
The increasing deployment of Federated Learning (FL) in Intrusion Detection Systems (IDS) introduces new challenges related to data privacy,...
Doron Shavit
Jailbreak prompts are a practical and evolving threat to large language models (LLMs), particularly in agentic systems that execute tools over...
Yuepeng Hu, Yuqi Jia, Mengyuan Li +2 more
In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user installs the tool and the LLM agent selects...
Hayfa Dhabhi, Kashyap Thimmaraju
Large Language Models (LLMs) deploy safety mechanisms to prevent harmful outputs, yet these defenses remain vulnerable to adversarial prompts. While...
Xiaoxu Peng, Dong Zhou, Jianwen Zhang +3 more
Vision Language Models (VLMs) have advanced perception in autonomous driving (AD), but they remain vulnerable to adversarial threats. These risks...
Tianyi Wang, Huawei Fan, Yuanchao Shu +2 more
Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest...
Zehua Cheng, Jianwei Yang, Wei Dai +1 more
Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for...
Haoran Ou, Kangjie Chen, Gelei Deng +4 more
Fact-checking systems with search-enabled large language models (LLMs) have shown strong potential for verifying claims by dynamically retrieving...
Chanwoo Park, Chanwoo Kim
Evasion attacks pose significant threats to AI systems, exploiting vulnerabilities in machine learning models to bypass detection mechanisms. The...
Nirhoshan Sivaroopan, Kanchana Thilakarathna, Albert Zomaya +6 more
Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that...
Qi Li, Xinchao Wang
Enabling large language models (LLMs) to solve complex reasoning tasks is a key step toward artificial general intelligence. Recent work augments...
Narek Maloyan, Dmitry Namiot
The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security...
Adeyemi Adeseye, Aisvarya Adeseye
Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources,...
Hongyan Chang, Ergute Bao, Xinjian Luo +1 more
Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt...
Harshil Parmar, Pushti Vyas, Prayers Khristi +1 more
As vulnerability research increasingly adopts generative AI, a critical reliance on opaque model outputs has emerged, creating a "trust gap" in...
Junda Lin, Zhaomeng Zhou, Zhi Zheng +4 more
LLM agents operating in open environments face escalating risks from indirect prompt injection, particularly within the tool stream where manipulated...
Jingxiao Yang, Ping He, Tianyu Du +2 more
Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable...
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