LLM agent limitations across vulnerability discovery, privacy preservation, scientific review, and browser use; plus on-device cohort inference, SLUB allocator exploitation, temporal HDR corruption, and adversarial DDoS detection.
Security analyses of ESXi VMKernel access control, detecting IMSI-catchers through causal messages, and simplifying Data-Oriented Programming in Linux.
DNS cache timing attacks for continuous user behavior monitoring, SMTP timeout manipulation for amplification attacks, co-training for dynamic password guessing, and performance-counter side channels on AMD SEV-SNP VMs.
Extracting website fingerprinting traces across positions, exploiting time synchronization in 802.11 for covert channels, breaking LLM watermarks with character perturbations, and characterizing censorship implementation in Chinese LLMs.
Misaligned models evading blocking monitors via prompt injections, a semantic cover story attack that reframes malicious behavior, inference engine fingerprinting by models, and a look at temporal graph reachability vs. observation.