ReplayAudit audits outsourced LLM fine-tuning via sealed records and selective replay
The system uses telemetry-guided sampling to audit training with 90% probability of detecting injected steps while reducing audit time by up to 67%.
Stories per day · 30 days
2 RSS
Relatedagents1deltastreamer1detection1fine-tuning1llm-auditing1memory1robotics1streaming-video1telemetry1video-understanding1vision1watermarking1
8 stories, newest first · one card per story
Stories tagged #replay
Dynamic watermarking detects replay attacks in vision controllers
RL policy balances watermark energy against control distortion on UR5 robot.
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
DeltaStreamer combines change-aware memory and targeted replay for streaming video question answering.
Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules
Cortex keeps coding-agent skills and rules only when replayed tests show a net gain.
Self-Preservation in Language Models
Qwen models can generate replay and sometimes choose tasks that better preserve prior capabilities.
EVISKILL: Grounding Skill Evolution in Replayable Evidence
EVISKILL uses replayable evidence so LLM agents can refine skills without updating model parameters.
CVE-2026-73636: Apache HTTP Server: mod_auth_digest one-time-nonce replay attack
Apache mod_auth_digest lets a MITM replay captured digest credentials through version 2.4.68.
Intrinsic-Extrinsic Coupling in Learning Dynamics
Researchers show replay can erase a classifier-head intervention's gains, formalizing intrinsic-extrinsic coupling in learning.