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 61–80 of 404 papers
Clear filtersRui Wen, Ahmed Salem, Andrew Paverd +2 more
Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves...
Vikash Singh, Debargha Ganguly, Aman Goel +5 more
Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal...
Hanyi Zhou, Chenyang Li, Yuanzhe Pang +3 more
Trusted Execution Environments (TEEs) offer a promising mechanism for safeguarding the intellectual property of on-device Large Language Models...
Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +2 more
Automatic safety judges -- systems such as Llama Guard or a GPT-4o grading prompt that decide whether a model's reply is harmful -- produce the...
Lingyu Li, Yan Teng, Yingchun Wang +1 more
Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet...
Adrita Rahman Tory, ABM Shawkat Ali, Md Abu Layek +1 more
Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its...
Ahmed Abdelnaby, Mohamed Elmahallawy
Deep neural networks (DNNs) are increasingly deployed in real-world vision systems, yet their predictions can be covertly manipulated by backdoor...
Ali Akarma, Toqeer Ali Syed, Muhammad Khan +2 more
As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and...
Bing Zheng, Zongyao Zhao, Wenming Yang
Generative engine optimization (GEO) enables content producers to increase the visibility of their web pages in generative search engines, but the...
Qingyu Meng, Yiwei Zha, Jiahuan Pei +3 more
Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling...
Jun He, Deying Yu
Persistent AI agents construct autobiographical state through reflection, retrieval, and consolidation. Persistence changes availability, not...
Stephanie Fong, Yiwen Jiang, Zimu Wang +12 more
Large Language Models (LLMs) are increasingly used in advice seeking and decision making that may affect social judgements. Despite stigma's profound...
Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2 more
Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior...
Jiaxuan Li, Jiahao Zhang, Duc Minh Vo +3 more
Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content...
Yizhe Zeng, Chenxu Niu, Wei Zhang +7 more
Backdoor attacks pose a serious threat to large language models (LLMs), but existing defenses remain fragmented, failing to pro?vide unified defense...
Dishu Yang, Jingjing Liu, Jize Li
Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence...
Chenhao Wu, Haoxuan Jia, Yang Liu +11 more
Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work,...
Mahshid Rezakhani, Kimia Azar, Hadi Kamali
The rapid advancement of large language models (LLMs) is driving a shift toward automated register transfer level (RTL) code generation, enabling...
Yanbo Dai, Zhenlan Ji, Zongjie Li +1 more
Tool-using LLM agents extend security risks beyond generated text to actions that affect external systems. Under multi-turn decomposition attacks, a...
Zhijie Zheng, Yu Li, Chen Qian +5 more
LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file...
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