AI Threat Alert
Survey MEDIUM
Adversarial Defense in Vision-Language Models: An Overview
Xiaowei Fu, Lei Zhang
The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible...
AI Security Research
2,077+ academic papers on AI security, attacks, and defenses
Total
2,077
Attack
809
Benchmark
603
Defense
272
Tool
226
Survey
113
Showing 381–400 of 986 papers
Clear filters Survey MEDIUM
De-Anonymization at Scale via Tournament-Style Attribution
Lirui Zhang, Huishuai Zhang
As LLMs rapidly advance and enter real-world use, their privacy implications are increasingly important. We study an authorship de-anonymization...
Benchmark MEDIUM
Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryption
Huanyi Ye, Jiale Guo, Ziyao Liu +1 more
RAG has emerged as a key technique for enhancing response quality of LLMs without high computational cost. In traditional architectures, RAG services...
Benchmark MEDIUM
Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers
Yixuan Du, Chenxiao Yu, Haoyan Xu +3 more
Vision-Language Models (VLMs) are rapidly replacing unimodal encoders in modern retrieval and recommendation systems. While their capabilities are...
Benchmark MEDIUM
Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
Xiaomei Zhang, Zhaoxi Zhang, Leo Yu Zhang +3 more
Visual token compression is widely adopted to improve the inference efficiency of Large Vision-Language Models (LVLMs), enabling their deployment in...
Tool MEDIUM
Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework
Zimo Ji, Daoyuan Wu, Wenyuan Jiang +5 more
Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based...
Benchmark MEDIUM
Gradient Structure Estimation under Label-Only Oracles via Spectral Sensitivity
Jun Liu, Leo Yu Zhang, Fengpeng Li +2 more
Hard-label black-box settings, where only top-1 predicted labels are observable, pose a fundamentally constrained yet practically important feedback...
Benchmark MEDIUM
Gradient Structure Estimation under Label-Only Oracles via Spectral Sensitivity
Jun Liu, Leo Yu Zhang, Fengpeng Li +2 more
Hard-label black-box settings, where only top-1 predicted labels are observable, pose a fundamentally constrained yet practically important feedback...
Attack MEDIUM
Building Production-Ready Probes For Gemini
János Kramár, Joshua Engels, Zheng Wang +4 more
Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful...
Attack MEDIUM
LoRA as Oracle
Marco Arazzi, Antonino Nocera
Backdoored and privacy-leaking deep neural networks pose a serious threat to the deployment of machine learning systems in security-critical...
Tool MEDIUM
Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
Kaiyu Zhou, Yongsen Zheng, Yicheng He +5 more
The agent--tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks...
Tool MEDIUM
SecMLOps: A Comprehensive Framework for Integrating Security Throughout the MLOps Lifecycle
Xinrui Zhang, Pincan Zhao, Jason Jaskolka +2 more
Machine Learning (ML) has emerged as a pivotal technology in the operation of large and complex systems, driving advancements in fields such as...
Attack MEDIUM
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
Christina Lu, Jack Gallagher, Jonathan Michala +2 more
Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We...
Survey MEDIUM
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Yi Liu, Weizhe Wang, Ruitao Feng +5 more
The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend...
Attack MEDIUM
The Straight and Narrow: Do LLMs Possess an Internal Moral Path?
Luoming Hu, Jingjie Zeng, Liang Yang +1 more
Enhancing the moral alignment of Large Language Models (LLMs) is a critical challenge in AI safety. Current alignment techniques often act as...
Tool MEDIUM
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
Yutao Mou, Zhangchi Xue, Lijun Li +4 more
While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks....
Defense MEDIUM
Understanding and Preserving Safety in Fine-Tuned LLMs
Jiawen Zhang, Yangfan Hu, Kejia Chen +7 more
Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential...
Survey MEDIUM
SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations
Mohoshin Ara Tahera, Karamveer Singh Sidhu, Shuvalaxmi Dass +1 more
Large Language Models (LLMs) are increasingly adopted in healthcare to support clinical decision-making, summarize electronic health records (EHRs),...
Tool MEDIUM
CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
Hanna Foerster, Tom Blanchard, Kristina Nikolić +6 more
AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss....
Benchmark MEDIUM
Blue Teaming Function-Calling Agents
Greta Dolcetti, Giulio Zizzo, Sergio Maffeis
We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three...
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