AI Threat Alert indexes 3,371+ 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 235 papers
Clear filtersQianlong Yang, Bowen Ye, Xianda Guo +4 more
Despite the progress of multimodal large language models (MLLMs), they continue to exhibit deficiencies in visual perception. Following visual...
Alireza Lotfi, Subangkar Karmaker Shanto, Imtiaz Karim +1 more
Autonomous agents are increasingly used to execute consequential tasks in environments governed by operational constraints, organizational policies,...
Ruiyang Zhang
Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call...
Siyuan Li, Aodu Wulianghai, Zehao Liu +8 more
Large Language Models (LLMs) are increasingly deployed in interactive settings, where user intent commonly unfolds through multi-turn dialogue....
Tobias Braun, Jonas Grebe, Louis Rethfeld +1 more
The widespread adoption of generative AI enables students to outsource cognitive effort to increasingly capable assistants, creating an illusion of...
Zheng Wu, Chenhao Xue, Shijie Zheng +3 more
As large language models (LLMs) continue to advance in complex reasoning tasks, they have learned to heavily prioritize explicit conditions provided...
Fazhong Liu, Zhuoyan Chen, Haozhen Tan +3 more
World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning...
Mingxiao Liu, Yitong Li, Haoren Zhao +6 more
Large Language Model (LLM)-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While...
Roberto Riaño, Gorka Abad, Stjepan Picek +1 more
Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to...
Spyridon Raptis, Haralampos-G. Stratigopoulos
Spiking Neural Networks (SNNs) communicate through sparse binary spike events rather than dense activations, enabling energy-efficient inference on...
Pingyu Wu, Lingyao Zhu, Weiming Zhang +1 more
Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks:...
Xiangyu Yin, Tora Bodin, Rohan Menon +1 more
Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder...
Nguyen Duc Thai, Junhao Dong, Sua Qi Rong +2 more
Vision-language models (VLMs), such as CLIP, are vulnerable to adversarial attacks, posing a serious problem for real-life applications and...
Muhammad Laiq
Timely identification of security-related bug reports is essential to minimize the window of vulnerabilities in software systems. Manually screening...
Cristian Leo, Anton Dykyi, Danny Cortegaca +2 more
Threat modeling is essential for secure software development, yet manual analysis of cloud-native architectures is slow and demands scarce security...
Benyamin Tafreshian, Prathamesh Dhake
Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically...
Yongjian Guo, Wanlun Ma, Lingyu Shen +2 more
Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers...
Xuanze Chen, Xukang Xie, Wentao Fu +3 more
Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious...
Petr Simecek, Elnaz Babayeva, Jiri Balhar +23 more
LLM-based analyzers have begun finding real vulnerabilities in mature open-source projects: AISLE's analyzer is credited with more than 280 CVEs...
Ruoyu Wang, Heng Zhao, Renjie Wu +4 more
Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned...
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 3,371+ 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