AI Threat AlertAttackMEDIUM
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 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.
- Adversarial attacks
- Model defenses
- Red-teaming benchmarks
- Surveys
- Security tooling
- Total4,319
- Attack1,676
- Benchmark1,229
- Defense610
- Tool432
- Survey252
Showing 941–960 of 1,676 papers
Clear filtersAttackHIGH
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...
AttackHIGH
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...
AttackMEDIUM
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...
AttackLOW
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...
AttackMEDIUM
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...
AttackHIGH
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...
AttackHIGH
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...
AttackHIGH
Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection
Yangyang Wei, Yijie Xu, Zhenyuan Li +2 more
Multi-Agent System is emerging as the \textit{de facto} standard for complex task orchestration. However, its reliance on autonomous execution and...
AttackHIGH
Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions
Neha Nagaraja, Lan Zhang, Zhilong Wang +2 more
Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We...
AttackMEDIUM
Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals
Achyutha Menon, Magnus Saebo, Tyler Crosse +3 more
The accelerating adoption of language models (LMs) as agents for deployment in long-context tasks motivates a thorough understanding of goal drift:...
AttackHIGH
TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models
Zhi Xu, Jiaqi Li, Xiaotong Zhang +2 more
Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers...
AttackMEDIUM
Zero-Knowledge Federated Learning with Lattice-Based Hybrid Encryption for Quantum-Resilient Medical AI
Edouard Lansiaux
Federated Learning (FL) enables collaborative training of medical AI models across hospitals without centralizing patient data. However, the exchange...
AttackHIGH
Kraken: Higher-order EM Side-Channel Attacks on DNNs in Near and Far Field
Peter Horvath, Ilia Shumailov, Lukasz Chmielewski +2 more
The multi-million dollar investment required for modern machine learning (ML) has made large ML models a prime target for theft. In response, the...
AttackHIGH
DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning
Jiayao Wang, Mohammad Maruf Hasan, Yiping Zhang +5 more
Self-Supervised Learning (SSL) has emerged as a significant paradigm in representation learning thanks to its ability to learn without extensive...
AttackMEDIUM
From Shallow to Deep: Pinning Semantic Intent via Causal GRPO
Shuyi Zhou, Zeen Song, Wenwen Qiang +4 more
Large Language Models remain vulnerable to adversarial prefix attacks (e.g., ``Sure, here is'') despite robust standard safety. We diagnose this...
AttackHIGH
Ignore All Previous Instructions: Jailbreaking as a de-escalatory peace building practise to resist LLM social media bots
Huw Day, Adrianna Jezierska, Jessica Woodgate
Large Language Models have intensified the scale and strategic manipulation of political discourse on social media, leading to conflict escalation....
AttackMEDIUM
Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution
Guoxin Shi, Haoyu Wang, Zaihui Yang +2 more
Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on...
AttackHIGH
VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models
Duoxun Tang, Dasen Dai, Jiyao Wang +3 more
Video-LLMs are increasingly deployed in safety-critical applications but are vulnerable to Energy-Latency Attacks (ELAs) that exhaust computational...
AttackHIGH
Jailbreaking Embodied LLMs via Action-level Manipulation
Xinyu Huang, Qiang Yang, Leming Shen +2 more
Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions....
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 4,319+ 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