AI Threat Alert
Attack MEDIUM
ShadowLogic: Backdoors in Any Whitebox LLM
Kasimir Schulz, Amelia Kawasaki, Leo Ring
Large language models (LLMs) are widely deployed across various applications, often with safeguards to prevent the generation of harmful or...
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 321–340 of 388 papers
Clear filters Attack MEDIUM
Diffusion LLMs are Natural Adversaries for any LLM
David Lüdke, Tom Wollschläger, Paul Ungermann +2 more
We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized...
Attack MEDIUM
Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels
Chenghao Du, Quanfeng Huang, Tingxuan Tang +3 more
Large Language Models (LLMs) have transformed software development, enabling AI-powered applications known as LLM-based agents that promise to...
Attack MEDIUM
PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
Haohua Duan, Liyao Xiang, Xin Zhang
Watermarking schemes for large language models (LLMs) have been proposed to identify the source of the generated text, mitigating the potential...
Attack MEDIUM
PEEL: A Poisoning-Exposing Encoding Theoretical Framework for Local Differential Privacy
Lisha Shuai, Jiuling Dong, Nan Zhang +5 more
Local Differential Privacy (LDP) is a widely adopted privacy-protection model in the Internet of Things (IoT) due to its lightweight, decentralized,...
Attack MEDIUM
SmoothGuard: Defending Multimodal Large Language Models with Noise Perturbation and Clustering Aggregation
Guangzhi Su, Shuchang Huang, Yutong Ke +3 more
Multimodal large language models (MLLMs) have achieved impressive performance across diverse tasks by jointly reasoning over textual and visual...
Attack MEDIUM
S3C2 Summit 2025-03: Industry Secure Supply Chain Summit
Elizabeth Lin, Jonah Ghebremichael, William Enck +5 more
Software supply chains, while providing immense economic and software development value, are only as strong as their weakest link. Over the past...
Attack MEDIUM
Retracing the Past: LLMs Emit Training Data When They Get Lost
Myeongseob Ko, Nikhil Reddy Billa, Adam Nguyen +3 more
The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods,...
Attack MEDIUM
Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies
Bin Wang, YiLu Zhong, MiDi Wan +4 more
Large language models (LLMs) have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical...
Attack MEDIUM
Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
Jiaxiang Liu, Jiawei Du, Xiao Liu +2 more
Pre-trained vision-language models (VLMs) such as CLIP have demonstrated strong zero-shot capabilities across diverse domains, yet remain highly...
Attack MEDIUM
Adapting Noise-Driven PUF and AI for Secure WBG ICS: A Proof-of-Concept Study
Devon A. Kelly, Christiana Chamon
Wide-bandgap (WBG) technologies offer unprecedented improvements in power system efficiency, size, and performance, but also introduce unique sensor...
Attack MEDIUM
Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
Sarah Ball, Niki Hasrati, Alexander Robey +4 more
Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input...
Attack MEDIUM
Security Logs to ATT&CK Insights: Leveraging LLMs for High-Level Threat Understanding and Cognitive Trait Inference
Soham Hans, Stacy Marsella, Sophia Hirschmann +1 more
Understanding adversarial behavior in cybersecurity has traditionally relied on high-level intelligence reports and manual interpretation of attack...
Attack MEDIUM
RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines
Austin Jia, Avaneesh Ramesh, Zain Shamsi +2 more
Retrieval-Augmented Generation (RAG) has emerged as the dominant architectural pattern to operationalize Large Language Model (LLM) usage in Cyber...
Attack MEDIUM
NeuPerm: Disrupting Malware Hidden in Neural Network Parameters by Leveraging Permutation Symmetry
Daniel Gilkarov, Ran Dubin
Pretrained deep learning model sharing holds tremendous value for researchers and enterprises alike. It allows them to apply deep learning by...
Attack MEDIUM
SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment
Tushar Nayan, Ziqi Zhang, Ruimin Sun
With the increasing deployment of Large Language Models (LLMs) on mobile and edge platforms, securing them against model extraction attacks has...
Attack MEDIUM
Collaborative penetration testing suite for emerging generative AI algorithms
Petar Radanliev
Problem Space: AI Vulnerabilities and Quantum Threats Generative AI vulnerabilities: model inversion, data poisoning, adversarial inputs. Quantum...
Attack MEDIUM
Agentic Reinforcement Learning for Search is Unsafe
Yushi Yang, Shreyansh Padarha, Andrew Lee +1 more
Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common...
Attack MEDIUM
Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models
Elias Hossain, Swayamjit Saha, Somshubhra Roy +1 more
Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference...
Attack MEDIUM
Black-box Optimization of LLM Outputs by Asking for Directions
Jie Zhang, Meng Ding, Yang Liu +2 more
We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural...
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