🎲 Fuzzing - amy.throwaway.lovely · Scour

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch 🛡️Exploit Mitigations

Bug-Report-Driven Fault Localization: Industrial Benchmarking and Lesson Learned at ABB Robotics ⚡JIT Exploitation

LLM-Guided Issue Generation from Uncovered Code Segments ⚡JIT Exploitation

Well-Conditioned Oblivious Perturbations in Linear Space 🧩Intermediate Representation

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers 🔌Hardware Security

AI Observability for Large Language Model Systems: A Multi-Layer Analysis of Monitoring Approaches from Confidence Calibration to Infrastructure Tracing 🔣Type Systems

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents 🛡️Exploit Mitigations

Test-Time Safety Alignment ✅Formal Verification

SAFEdit: Does Multi-Agent Decomposition Resolve the Reliability Challenges of Instructed Code Editing? ⚡JIT Exploitation

A-IC3: Learning-Guided Adaptive Inductive Generalization for Hardware Model Checking ✅Formal Verification

One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety 🧩Intermediate Representation

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models 💾Binary Analysis

What Is the Cost of Energy Monitoring? An Empirical Study on the Overhead of RAPL-Based Tools 🔒CFI

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models ⚡JIT Exploitation

Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents 🌊Dataflow Analysis

AsmRAG: LLM-Driven Malware Detection by Retrieving Functionally Similar Assembly Code 💾Binary Analysis

eDySec: A Deep Learning-based Explainable Dynamic Analysis Framework for Detecting Malicious Packages in PyPI Ecosystem 💾Binary Analysis

Vulnerability Identification by Harnessing Inter-connected Multi-Source Information 🛡️Vulnerability Research

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study 🐧Kernel Exploitation

From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Model 🛡️Exploit Mitigations

Log in to enable infinite scrolling