AI Threat Alert
Attack MEDIUM
Exclusive Unlearning
Mutsumi Sasaki, Kouta Nakayama, Yusuke Miyao +2 more
When introducing Large Language Models (LLMs) into industrial applications, such as healthcare and education, the risk of generating harmful content...
AI Security Research
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.
- Adversarial attacks
- Model defenses
- Red-teaming benchmarks
- Surveys
- Security tooling
- Total3,023
- Attack1,175
- Benchmark866
- Defense407
- Tool319
- Survey176
Showing 121–140 of 388 papers
Clear filters Attack MEDIUM
Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment
Xaver Fink, Borja Fernandez Adiego, Daniele Mirarchi +4 more
In this paper, we analyze and improve the adversarial robustness of a convolutional neural network (CNN) that assists crystal-collimator alignment at...
Attack MEDIUM
Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange
Vinod Vaikuntanathan, Or Zamir
AI agents are increasingly deployed to interact with other agents on behalf of users and organizations. We ask whether two such agents, operated by...
Attack MEDIUM
Semantics Over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities
Qiqing Huang, Xingyu Wang, Wanda Guo +2 more
Modern 5G user equipment (UE) processes Radio Resource Control (RRC) configuration messages during early control-plane exchanges, before...
Attack MEDIUM
Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning
Aobo Chen, Chenxu Zhao, Chenglin Miao +1 more
Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further...
Attack MEDIUM
AEGIS: Adversarial Entropy-Guided Immune System -- Thermodynamic State Space Models for Zero-Day Network Evasion Detection
Vickson Ferrel
As TLS 1.3 encryption limits traditional Deep Packet Inspection (DPI), the security community has pivoted to Euclidean Transformer-based classifiers...
Attack MEDIUM
Performative Scenario Optimization
Quanyan Zhu, Zhengye Han
This paper introduces a performative scenario optimization framework for decision-dependent chance-constrained problems. Unlike classical stochastic...
Attack MEDIUM
FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation
Ruiyang Wang, Rong Pan, Zhengan Yao
Federated learning (FL) enables distributed clients to collaboratively train a global model using local private data. Nevertheless, recent studies...
Attack MEDIUM
Bridging Code Property Graphs and Language Models for Program Analysis
Ahmed Lekssays
Large Language Models (LLMs) face critical challenges when analyzing security vulnerabilities in real world codebases: token limits prevent loading...
Attack MEDIUM
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
Huamin Chen, Xunzhuo Liu, Bowei He +5 more
Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing,...
Attack MEDIUM
Reward Sharpness-Aware Fine-Tuning for Diffusion Models
Kwanyoung Kim, Byeongsu Sim
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the...
Attack MEDIUM
Detection of adversarial intent in Human-AI teams using LLMs
Abed K. Musaffar, Ambuj Singh, Francesco Bullo
Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval,...
Attack MEDIUM
Memory poisoning and secure multi-agent systems
Vicenç Torra, Maria Bras-Amorós
Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large...
Attack MEDIUM
Graph-Aware Text-Only Backdoor Poisoning for Text-Attributed Graphs
Qi Luo, Minghui Xu, Dongxiao Yu +1 more
Many learning systems now use graph data in which each node also contains text, such as papers with abstracts or users with posts. Because these...
Attack MEDIUM
Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
Dong-Xiao Zhang, Hu Lou, Jun-Jie Zhang +2 more
Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems, each addressed with...
Attack MEDIUM
Retrieval-Augmented LLMs for Security Incident Analysis
Xavier Cadet, Aditya Vikram Singh, Harsh Mamania +6 more
Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sources, including intrusion detection alerts,...
Attack MEDIUM
Retrieval-Augmented LLMs for Security Incident Analysis
Xavier Cadet, Aditya Vikram Singh, Harsh Mamania +6 more
Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sources, including intrusion detection alerts,...
Attack MEDIUM
Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare
Saikat Maiti
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system...
Attack MEDIUM
Towards Unsupervised Adversarial Document Detection in Retrieval Augmented Generation Systems
Patrick Levi
Retrieval augmented generation systems have become an integral part of everyday life. Whether in internet search engines, email systems, or service...
Attack MEDIUM
An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
Kushankur Ghosh, Mehar Klair, Kian Kyars +2 more
Provenance graphs model causal system-level interactions from logs, enabling anomaly detectors to learn normal behavior and detect deviations as...
Frequently asked questions
What is AI security research?
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.
How many AI security papers does AI Threat Alert track?
AI Threat Alert indexes 3,023+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Where do the research papers come from?
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.
What topics does the AI security research cover?
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.
How is this different from a generic paper search?
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.
Track AI security vulnerabilities in real time
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