AI Threat Alert
Benchmark HIGH
Red Teaming Large Reasoning Models
Jiawei Chen, Yang Yang, Chao Yu +6 more
Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical...
AI Security Research
2,529+ academic papers on AI security, attacks, and defenses
Total
2,529
Attack
969
Benchmark
729
Defense
345
Tool
272
Survey
142
Showing 501–520 of 551 papers
Clear filters Benchmark MEDIUM
Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities
Aayush Garg, Zanis Ali Khan, Renzo Degiovanni +1 more
Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models (LLMs) present promising...
Benchmark LOW
TIM-PRM: Verifying multimodal reasoning with Tool-Integrated PRM
Peng Kuang, Xiangxiang Wang, Wentao Liu +2 more
Multimodal Large Language Models (MLLMs) have achieved impressive performances in mathematical reasoning, yet they remain vulnerable to visual...
Benchmark MEDIUM
Watermarks for Embeddings-as-a-Service Large Language Models
Anudeex Shetty
Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs,...
Benchmark MEDIUM
Ghosting Your LLM: Without The Knowledge of Your Gradient and Data
Abeer Matar A. Almalky, Ziyan Wang, Mohaiminul Al Nahian +2 more
In recent years, large language models (LLMs) have achieved substantial advancements and are increasingly integrated into critical applications...
Benchmark MEDIUM
CacheTrap: Injecting Trojans in LLMs without Leaving any Traces in Inputs or Weights
Mohaiminul Al Nahian, Abeer Matar A. Almalky, Gamana Aragonda +6 more
Adversarial weight perturbation has emerged as a concerning threat to LLMs that either use training privileges or system-level access to inject...
Benchmark MEDIUM
Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
Gauri Pradhan, Joonas Jälkö, Santiago Zanella-Bèguelin +1 more
Training machine learning models with differential privacy (DP) limits an adversary's ability to infer sensitive information about the training data....
Benchmark LOW
MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning
Junjian Wang, Lidan Zhao, Xi Sheryl Zhang
Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where...
Benchmark MEDIUM
The Phish, The Spam, and The Valid: Generating Feature-Rich Emails for Benchmarking LLMs
Rebeka Toth, Tamas Bisztray, Nils Gruschka
In this paper, we introduce a metadata-enriched generation framework (PhishFuzzer) that seeds real emails into Large Language Models (LLMs) to...
Benchmark MEDIUM
Constructing and Benchmarking: a Labeled Email Dataset for Text-Based Phishing and Spam Detection Framework
Rebeka Toth, Tamas Bisztray, Richard Dubniczky
Phishing and spam emails remain a major cybersecurity threat, with attackers increasingly leveraging Large Language Models (LLMs) to craft highly...
Benchmark MEDIUM
RaX-Crash: A Resource Efficient and Explainable Small Model Pipeline with an Application to City Scale Injury Severity Prediction
Di Zhu, Chen Xie, Ziwei Wang +1 more
New York City reports over one hundred thousand motor vehicle collisions each year, creating substantial injury and public health burden. We present...
Benchmark MEDIUM
PILOT: Command-line Interface Fuzzing via Path-Guided, Iterative Large Language Model Prompting
Momoko Shiraishi, Yinzhi Cao, Takahiro Shinagawa
Command-line interface (CLI) fuzzing tests programs by mutating both command-line options and input file contents, thus enabling discovery of...
Benchmark MEDIUM
APT-CGLP: Advanced Persistent Threat Hunting via Contrastive Graph-Language Pre-Training
Xuebo Qiu, Mingqi Lv, Yimei Zhang +4 more
Provenance-based threat hunting identifies Advanced Persistent Threats (APTs) on endpoints by correlating attack patterns described in Cyber Threat...
Benchmark MEDIUM
Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?
David Amebley, Sayanton Dibbo
In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data...
Benchmark MEDIUM
DUALGUAGE: Automated Joint Security-Functionality Benchmarking for Secure Code Generation
Abhijeet Pathak, Suvadra Barua, Dinesh Gudimetla +4 more
Large language models (LLMs) and autonomous coding agents are increasingly used to generate software across a wide range of domains. Yet a core...
Benchmark MEDIUM
Synthetic Data: AI's New Weapon Against Android Malware
Angelo Gaspar Diniz Nogueira, Kayua Oleques Paim, Hendrio Bragança +2 more
The ever-increasing number of Android devices and the accelerated evolution of malware, reaching over 35 million samples by 2024, highlight the...
Benchmark MEDIUM
Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion
Yu Cui, Yifei Liu, Hang Fu +4 more
Research on the safety evaluation of large language models (LLMs) has become extensive, driven by jailbreak studies that elicit unsafe responses....
Benchmark MEDIUM
Can LLMs Recover Program Semantics? A Systematic Evaluation with Symbolic Execution
Rong Feng, Suman Saha
Obfuscation poses a persistent challenge for software engineering tasks such as program comprehension, maintenance, testing, and vulnerability...
Benchmark MEDIUM
Medical Malice: A Dataset for Context-Aware Safety in Healthcare LLMs
Andrew Maranhão Ventura D'addario
The integration of Large Language Models (LLMs) into healthcare demands a safety paradigm rooted in \textit{primum non nocere}. However, current...
Benchmark LOW
LLM-CSEC: Empirical Evaluation of Security in C/C++ Code Generated by Large Language Models
Muhammad Usman Shahid, Chuadhry Mujeeb Ahmed, Rajiv Ranjan
The security of code generated by large language models (LLMs) is a significant concern, as studies indicate that such code often contains...
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