Papers › From Zero to Hero: Cold-Start Anomaly Detection

From Zero to Hero: Cold-Start Anomaly Detection

30 May 2024arXiv:2405.20341archive 2025-07-28

Tal Reiss, George Kour, Naama Zwerdling, Ateret Anaby-Tavor, Yedid Hoshen

When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such "cold-start" cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics.

PaperPDFCode

Code

talreiss/coldfusion officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionCold-Start Anomaly Detectionzero-shot anomaly detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cold-Start Anomaly Detection BANKING77-OOS ColdFusion AUC 10% 81.7 #1 of 3 Archive leaderboard report
Cold-Start Anomaly Detection BANKING77-OOS ZS AUC 10% 78.9 #2 of 3 Archive leaderboard report
Cold-Start Anomaly Detection BANKING77-OOS DN2 AUC 10% 76.7 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections