AI Threat AlertDefenseMEDIUM
DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
Bo Jiang
Knowledge distillation from proprietary LLM APIs poses a growing threat to model providers, yet defenses against this attack remain fragmented and...
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 361–380 of 610 papers
Clear filtersDefenseMEDIUM
VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription
Sumit Ranjan, Sugandha Sharma, Ubaid Abbas +1 more
Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt...
DefenseMEDIUM
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
Xisen Jin, Michael Duan, Qin Lin +4 more
As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces...
DefenseMEDIUM
Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
Jinman Wu, Yi Xie, Shen Lin +2 more
Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the...
DefenseMEDIUM
Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment
Ved Sriraman, Adam Block
Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a...
DefenseLOW
Hierarchical Decoding for Discrete Speech Synthesis with Multi-Resolution Spoof Detection
Junchuan Zhao, Minh Duc Vu, Ye Wang
Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and...
DefenseMEDIUM
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...
DefenseMEDIUM
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...
DefenseLOW
Molt Dynamics: Emergent Social Phenomena in Autonomous AI Agent Populations
Brandon Yee, Krishna Sharma
MoltBook is a large-scale multi-agent coordination environment where over 770,000 autonomous LLM agents interact without human participation,...
DefenseLOW
RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection
Sami Abuzakuk, Lucas Crijns, Anne-Marie Kermarrec +2 more
Infrastructure as code (IaC) tools automate cloud provisioning but verifying that deployed systems remain consistent with the IaC specifications...
DefenseLOW
ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense
Nancy Lau, Louis Sloot, Jyoutir Raj +6 more
Large language models (LLMs) are increasingly being deployed as software engineering agents that autonomously contribute to repositories. A major...
DefenseMEDIUM
Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision
Manisha Mukherjee, Vincent J. Hellendoorn
Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development, yet their limited transparency in...
DefenseMEDIUM
Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
Ming Wen, Kun Yang, Xin Chen +4 more
Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as...
DefenseMEDIUM
TAS-GNN: A Status-Aware Signed Graph Neural Network for Anomaly Detection in Bitcoin Trust Systems
Chang Xue, Fang Liu, Jiaye Wang +2 more
Decentralized financial platforms rely heavily on Web of Trust reputation systems to mitigate counterparty risk in the absence of centralized...
DefenseLOW
Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
Xingyu Zhu, Kesen Zhao, Liang Yi +4 more
Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning, yet they remain vulnerable to hallucination,...
DefenseLOW
LLM-Powered Silent Bug Fuzzing in Deep Learning Libraries via Versatile and Controlled Bug Transfer
Kunpeng Zhang, Dongwei Xiao, Daoyuan Wu +5 more
Deep learning (DL) libraries are widely used in critical applications, where even subtle silent bugs can lead to serious consequences. While existing...
DefenseMEDIUM
Secure Semantic Communications via AI Defenses: Fundamentals, Solutions, and Future Directions
Lan Zhang, Chengsi Liang, Zeming Zhuang +4 more
Semantic communication (SemCom) redefines wireless communication from reproducing symbols to transmitting task-relevant semantics. However, this...
DefenseMEDIUM
MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
Xuan Chen, Hao Liu, Tao Yuan +3 more
Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. While recent...
DefenseMEDIUM
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek V. Datla, Anoop Kumar +4 more
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct...
DefenseMEDIUM
A Lightweight Defense Mechanism against Next Generation of Phishing Emails using Distilled Attention-Augmented BiLSTM
Morteza Eskandarian, Mahdi Rabbani, Arun Kaniyamattam +6 more
The current generation of large language models produces sophisticated social-engineering content that bypasses standard text screening systems in...
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