Infostealer data-driven analysis, LLM honeypots, persistent billable state DoW, bypassing unlearning via tokenization, DistillGuard for NPM, MoSign VR authentication, AgentKernel native trust, and Byzantine-robust intrusion detection.
New vulnerabilities in eBPF, WebGPU fuzzing, and backdoor attacks on LLM-powered robots.
New findings on diffusion model membership inference, distributed system fuzzing, LLM safety alignment limitations, BLE re-pairing flaws, and hypervisor cross-domain exploitation.
LLM agents are central today, revealing new architectural risks like capability laundering and the stochastic deputy problem, while hardware vulnerabilities expand into GPU memory architectures.