AI Threat Alert
Attack MEDIUM
Good-Enough LLM Obfuscation (GELO)
Anatoly Belikov, Ilya Fedotov
Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can observe KV...
AI Security Research
AI Threat Alert indexes 3,082+ 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
- Total3,082
- Attack1,196
- Benchmark883
- Defense421
- Tool321
- Survey181
Showing 1221–1240 of 3,082 papers
Defense MEDIUM
ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts
Trapoom Ukarapol, Nut Chukamphaeng, Kunat Pipatanakul +1 more
The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded...
Other LOW
Causally Robust Reward Learning from Reason-Augmented Preference Feedback
Minjune Hwang, Yigit Korkmaz, Daniel Seita +1 more
Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it...
Benchmark MEDIUM
Osmosis Distillation: Model Hijacking with the Fewest Samples
Yuchen Shi, Huajie Chen, Heng Xu +6 more
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources....
Attack HIGH
Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models
Yuanbo Li, Tianyang Xu, Cong Hu +3 more
The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also...
Attack HIGH
Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models
Yuanbo Li, Tianyang Xu, Cong Hu +3 more
The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also...
Survey MEDIUM
Design Behaviour Codes (DBCs): A Taxonomy-Driven Layered Governance Benchmark for Large Language Models
G. Madan Mohan, Veena Kiran Nambiar, Kiranmayee Janardhan
We introduce the Dynamic Behavioral Constraint (DBC) benchmark, the first empirical framework for evaluating the efficacy of a structured,...
Tool LOW
Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization
Furkan Mumcu, Yasin Yilmaz
As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to...
Attack MEDIUM
Efficient Refusal Ablation in LLM through Optimal Transport
Geraldin Nanfack, Eugene Belilovsky, Elvis Dohmatob
Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent...
Benchmark MEDIUM
PTOPOFL: Privacy-Preserving Personalised Federated Learning via Persistent Homology
Kelly L Vomo-Donfack, Adryel Hoszu, Grégory Ginot +1 more
Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions...
Survey LOW
When AI Fails, What Works? A Data-Driven Taxonomy of Real-World AI Risk Mitigation Strategies
Evgenija Popchanovska, Ana Gjorgjevikj, Maryan Rizinski +3 more
Large language models (LLMs) are increasingly embedded in high-stakes workflows, where failures propagate beyond isolated model errors into systemic...
Benchmark MEDIUM
Code Fingerprints: Disentangled Attribution of LLM-Generated Code
Jiaxun Guo, Ziyuan Yang, Mengyu Sun +3 more
The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale. While...
Attack LOW
Bayesian Adversarial Privacy
Cameron Bell, Timothy Johnston, Antoine Luciano +1 more
Theoretical and applied research into privacy encompasses an incredibly broad swathe of differing approaches, emphasis and aims. This work introduces...
Tool HIGH
CAM-LDS: Cyber Attack Manifestations for Automatic Interpretation of System Logs and Security Alerts
Max Landauer, Wolfgang Hotwagner, Thorina Boenke +2 more
Log data are essential for intrusion detection and forensic investigations. However, manual log analysis is tedious due to high data volumes,...
Tool MEDIUM
A Multi-Dimensional Quality Scoring Framework for Decentralized LLM Inference with Proof of Quality
Arther Tian, Alex Ding, Frank Chen +2 more
Decentralized large language model (LLM) inference networks can pool heterogeneous compute to scale serving, but they require lightweight and...
Attack MEDIUM
From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
Yizhe Xie, Congcong Zhu, Xinyue Zhang +5 more
Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative...
Attack HIGH
When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
Junchen Li, Chao Qi, Rongzheng Wang +5 more
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge, but its reliance...
Attack HIGH
Structure-Aware Distributed Backdoor Attacks in Federated Learning
Wang Jian, Shen Hong, Ke Wei +1 more
While federated learning protects data privacy, it also makes the model update process vulnerable to long-term stealthy perturbations. Existing...
Benchmark MEDIUM
In-Context Environments Induce Evaluation-Awareness in Language Models
Maheep Chaudhary
Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit...
Defense MEDIUM
Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
Zeyu Zhang, Xiangxiang Dai, Ziyi Han +2 more
Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during...
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 3,082+ 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