DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation

• URL: http://arxiv.org/abs/2606.28725v1
• Date: Sat, 27 Jun 2026 04:10:45 GMT
• Title: DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation
• Abstract summary: This paper introduces DriftGuard, a safety-aware adaptive moderation framework that combines multi-monitor drift detection with selective model updating.<n>The framework tracks global text drift, identity-harm drift, model uncertainty, toxic-risk drift, and false-negative-risk drift.
• Score: 0.6263481844384227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated toxicity moderation systems operate in dynamic online environments where harmful behavior evolves through coded language, shifting targets, and strategic adaptation to enforcement. Existing drift detection methods often focus on global distributional change, but such signals may miss safety-relevant shifts that emerge in localized harm subspaces or high-risk model-error regions. This paper introduces DriftGuard, a safety-aware adaptive moderation framework that combines multi-monitor drift detection with selective model updating. The framework tracks global text drift, identity-harm drift, model uncertainty, toxic-risk drift, and false-negative-risk drift. When safety-relevant change is detected, the model is updated using a hard-mix adaptation set that prioritizes likely false negatives, identity-related high-risk examples, false-positive-risk examples, and uncertain boundary cases. Experiments on Civil Comments temporal shift and Jigsaw-to-DynaHate cross-dataset shift show that safety-aware monitors detect risks missed by global drift alone. Hard-mix adaptation improves toxic recall and accuracy over no-update and random-balanced baselines, raising toxic recall to 0.8777 on Civil Comments and from 0.7107 to 0.8523 on DynaHate. Bootstrap analysis further shows stable DynaHate safety gains, with toxic recall increasing by 0.1418 and false-negative prevalence decreasing by 0.0781. Overall, DriftGuard links safety-aware drift detection to targeted, lightweight model updating for more robust adaptive toxicity moderation.

Related papers

• Adaptive Intrusion Detection System using Transformer-Based Neural Networks and Continual Learning Approach with Adversarial Investigation [1.90296757424868]
  Network intrusion detection systems (IDS) trained on fixed traffic snapshots decay silently after deployment as threat distributions shift.<n>Replay-based continual learning counters this, but existing methods unrealistically confine benign traffic to a single early task and ignore the replay buffer as a potential attack surface.<n>We introduce the class-instance incremental (CII) scenario where benign flows alongside new attacks as a more faithful stress test, and probe the buffer with overt label flipping and stealthy backdoor poisoning attacks.
  arXiv  Detail & Related papers  (2026-08-05T09:06:45Z)
• Task-Aligned Stability Analysis of Vision-Language Models for Autonomous Driving Hazard Detection [0.0]
  We study whether corruption-induced embedding drift predicts changes in a task-aligned hazard score derived from CLIP image-text similarities.<n>Using controlled corruptions on BDD100K road scenes, we compare embedding drift against margin drift.<n>Some families exhibit strong coupling between representation drift and decision drift, while others induce hazardous decision instability despite relatively modest embedding change.
  arXiv  Detail & Related papers  (2026-06-10T10:20:14Z)
• Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation [52.122731171289665]
  We introduce the first framework for cross-model safety steering.<n>Our pipeline never accesses unsafe data on the target side.<n>We evaluate our approach in text-to-image and text-to-video generation across diverse source-target model pairs.
  arXiv  Detail & Related papers  (2026-06-03T18:00:04Z)
• CBANet: A Compact Attention-Based CNN-BiLSTM Network for Aggressive Driving Event Detection [7.82687682320363]
  Aggressive driving is a major cause of traffic accidents and poses a serious threat to road safety.<n>Deep learning methods have shown promising results in detecting risky driving behaviours from vehicle sensor data.<n>But their performance in real-world conditions is often limited by severe data imbalance, large variability between drivers, and the lack of physically interpretable vehicle dynamics representations.
  arXiv  Detail & Related papers  (2026-05-22T10:30:28Z)
• Selective Safety Steering via Value-Filtered Decoding [54.87935112120107]
  Large language models (LLMs) are trained to align with human values, but their generations may still violate safety constraints.<n>Existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model.<n>We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses.
  arXiv  Detail & Related papers  (2026-05-14T12:13:08Z)
• Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability [79.08785366532287]
  We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability.<n>We evaluate the approach in two safety-critical partially observable domains: automated glucose regulation and safety-constrained navigation.
  arXiv  Detail & Related papers  (2026-05-14T01:23:09Z)
• ThreatFormer-IDS: Robust Transformer Intrusion Detection with Zero-Day Generalization and Explainable Attribution [0.0]
  Intrusion detection in IoT and industrial networks requires models that can detect rare attacks at low false-positive rates while remaining reliable under evolving traffic and limited labels.<n>We propose ThreatFormer- IDS, a Transformer-based sequence modeling framework that converts flow records into time-ordered windows and learns contextual representations for robust intrusion screening.<n>On the ToN IoT benchmark with chronological evaluation, ThreatFormer-IDS achieves AUCROC 0.994, AUC-PR 0.956, and Recall@1%FPR 0.910, outperforming strong tree-based and sequence baselines.
  arXiv  Detail & Related papers  (2026-02-26T23:20:42Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• How Much Is Too Much? Adaptive, Context-Aware Risk Detection in Naturalistic Driving [0.6299766708197883]
  We propose a unified, context-aware framework that adapts labels and models over time and across drivers.<n>The framework is tested using two safety indicators, speed-weighted headway and harsh driving events, and three models: Random Forest, XGBoost, and Deep Neural Network (DNN)<n>Overall, the framework shows promise for adaptive, context-aware risk detection that can enhance real-time safety feedback and support driver-focused interventions in intelligent transportation systems.
  arXiv  Detail & Related papers  (2025-07-26T16:24:25Z)
• Shape it Up! Restoring LLM Safety during Finetuning [65.75757313781104]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Sample-Efficient Safety Assurances using Conformal Prediction [57.92013073974406]
  Early warning systems can provide alerts when an unsafe situation is imminent. To reliably improve safety, these warning systems should have a provable false negative rate. We present a framework that combines a statistical inference technique known as conformal prediction with a simulator of robot/environment dynamics.
  arXiv  Detail & Related papers  (2021-09-28T23:00:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.