Weaponizing the Exit: Input Privacy Leakage via Exit Routing Manipulation in Multi-Exit Networks
Multi-exit networks improve inference efficiency by allowing inputs to terminate early at intermediate exits. We identif
2026-10-24 归档
今日共收录 814 条安全情报，包含 0 个 CVE，421 篇安全通告，以及 100 篇研究论文。
← 返回归档列表SecLog-Bench: A Scalable Benchmark for Cybersecurity Log Reasoning with Scaffolded Evidence
Large language models (LLMs) have shown strong potential for cybersecurity, leading to growing interest in LLM-based aut
Bridging Number-Theoretic Primality Testing And Algorithmic Optimization: An Adaptive Cryptographic Framework
The security of modern public-key cryptographic systems, such as RSA, Diffie-Hellman, and ECC, depends entirely on the c
Amplifying Latency and Cost of LLM Inference via Rowhammer Attack
Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time (JI
Model-intrinsic, Weight-level, and Training-free Spectral Fingerprinting for Large Language Models
The increasing release and reuse of Large Language Models (LLMs) as open-weight checkpoints make model fingerprinting im
HiMark: Hierarchical and Controllable Multi-bit Watermarking for Large Language Models
With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly diff
Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as te
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled
Data-Void Exploits in Web-Searching LLMs
Web-searching Large Language Models (LLMs) have changed how users seek online information: instead of sifting through ra
PhishGen: Understanding LLM Capabilities in Automated Phishing Website Generation
Phishing relies on visual deception, traditionally requiring web-development skills or pre-built kits. LLMs erode this b
Prompt Injection Through Forensic Evidence: A Taxonomy and Proof of Concept of Anti-Forensic Attacks on LLM-Assisted Digital Investigations
Large language models (LLMs) are entering digital forensics as examination assistants and autonomous agents. Digital for
MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (
CertMoE: Robustness Certification for Mixture-of-Experts LLMs via Routing-Aware Smoothing
Provable robustness is a cornerstone of trustworthy machine learning, aiming to guarantee model predictions under advers
Where AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden Vulnerabilities
LLM-based vulnerability discovery harnesses can miss real, reachable vulnerabilities because of how the harness around t
Beyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics
Current LLM safety benchmarks predominantly rely on binary safe or unsafe labels, lacking explanatory depth and sufferin
Cryptanalysis and Repair of "Decentralized Multi-authority ABE for NC$^1$ from BDH"
We present a plaintext-recovery attack on the decentralized multi-authority attribute-based encryption construction of D
Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning
Large language model (LLM) agents are increasingly deployed in multi-agent systems (MAS) to accomplish complex tasks. Pr
Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt inje
How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery
How much does an agent harness affect vulnerability discovery, and does its value depend on the model? We study 24 model
CALLIOPE: Private Insights into AI Use, Without Embeddings
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g