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 361–380 of 1,983 papers
Clear filtersHuijun Zhou, Xiaohan Zhang, Haozhe Zhang +3 more
The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments...
Jianan Ma, Xiaohu Du, Ruixiao Lin +8 more
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe,...
Xiang Chen, Yuxian Dong, Chao Li +6 more
Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared...
Jingyi Kang, Junyu Lu, Bo Xu +4 more
Large language models (LLMs) require robust toxicity evaluation beyond explicit wording. This setting remains underexplored in Chinese, where...
Chengyan Ma, Jieke Shi, Ruidong Han +4 more
Trusted Execution Environments (TEEs) provide hardware-based isolation to protect sensitive data and computations from potentially compromised...
Chengyan Ma, Jieke Shi, Ruidong Han +3 more
Trusted Execution Environments (TEEs) provide hardware-enforced isolation that protects sensitive code and data from untrusted software. Despite...
Ziyuan Chen, Yueming Lyu, Yi Liu +4 more
While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks. Existing...
Zhi Chen, Shehab Sarar Ahmed, Chenkai Wang +2 more
Congestion controllers (CCs) are critical to network performance, and yet their robustness under adverse conditions remains insufficiently...
Andy Han, Kristina Fujimoto, Avidan Shah +5 more
Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings....
Aman Saxena, Jan Schuchardt, Yan Scholten +1 more
Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training...
Ze Sheng, Zhicheng Chen, Qingxiao Xu +2 more
Software vulnerabilities pose critical security threats, with nearly 50,000 CVEs reported in 2025. While Large Language Models (LLMs) show promise...
Danyu Sun, Jinghuai Zhang, Yuan Tian +1 more
Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing...
Giorgio Piras, Raffaele Mura, Fabio Brau +4 more
Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal...
Shahnewaz Karim Sakib, Swati Kar, Anindya Bijoy Das
Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks...
Heajun An, Qi Zhang, Vedanth Achanta +1 more
Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating information seeking, advice, and emotionally...
Roland Pihlakas, Jan Llenzl Dagohoy
Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in...
Pengyu Sun, Qishu Jin, Enhao Huang +4 more
Model Context Protocol (MCP) has emerged as a standard interface for connecting LLM agents to external tools. Because MCP servers expose privileged...
Abdullah Al Nomaan Nafi, Fnu Suya, Swarup Bhunia +1 more
Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial...
Samuele Pasini, Jinhan Kim, Paolo Tonella
Modern DNNs are repeatedly fine-tuned to incorporate new data and functionality. This evolutionary workflow introduces a security risk when updated...
Scott Freitas, Amir Gharib
Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft...
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