arXiv Brief — 2026-09-24
New perspectives on LLM cryptographic capabilities, agent oversight bypasses, and hardware fuzzing paradigms.
Fuzzing
arXiv Brief — 2026-09-23
New vulnerabilities in eBPF, WebGPU fuzzing, and backdoor attacks on LLM-powered robots.
Conference Brief — 2026-09-23
New findings spanning LLM cache poisoning, npm prototype pollution, and kernel compartmentalization with PKS.
Conference Brief — 2026-09-22
New findings on diffusion model membership inference, distributed system fuzzing, LLM safety alignment limitations, BLE re-pairing flaws, and hypervisor cross-domain exploitation.
Conference Brief — 2026-09-20
New findings spanning library fuzzing, BACnet protocol vulnerabilities, OLE document security, backdoors in machine learning, risks in AI character platforms, and cloud app-in-app resource isolation.