TRACE ranks CVE-to-ATT&CK mappings with constrained multi-evidence
Candidate construction cuts a 201-technique space by about 60% while retaining a ground-truth technique for 95.11%–100% of CVEs.
Stories per day · 30 days
1 RSS
Relatedattck1cve-mapping1machine-unlearning1model-snapshots1privacy1ranking1text-reconstruction1threat-intelligence1
10 stories, newest first · one card per story
Stories tagged #trace
TRACE reconstructs unlearned LLM text from pre- and post-unlearning snapshots
The attack needs no data-specific prior and was tested on TOFU, MUSE, and WMDP with six unlearning methods.
One Node, Two Roles: Simultaneous Contests for Validation and Attention in Rollups
Coupled contest analysis finds TRACE can raise optimistic-rollup execution diversity more than Proof of Diligence.
Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
On TRACE's 590 AppWorld boundaries, recent agent history only weakly predicts harmful context compaction.
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
TRACE aligns FP4 train and rollout paths for MoE RL, matching BF16 quality with up to 5.4x rollout speedup.
TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety
TRACE cut multi-turn attack success to the lowest rate in all 35 model-attack pairs with at most a 1.23-point utility drop.
TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
TRACE benchmarks streaming video models on timing, triggers, workload, and reliability, not accuracy alone.
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
TRACE reconstructs private embodied observation-action trajectories from policy gradients, reaching 18.8 dB PSNR.
Linux Foundation Introduces TRACE Standard for AI Runtime Evidence
The Linux Foundation introduced TRACE, an open standard providing hardware-attested runtime and compliance evidence for AI agents.
Linux Foundation takes on TRACE, a hardware-backed runtime evidence specification for AI agents
The Linux Foundation adopts TRACE, an OPAQUE-contributed spec giving AI agents hardware-attested, cryptographically verifiable runtime and compliance evidence.
2