{
  "id": 298,
  "url": "https://arxiv.org/abs/2607.02903v1",
  "title": "TIER: Trajectory-Invariant Explanation Regularization for Membership Privacy",
  "summary": "Explainability is central to building trustworthy AI, yet explanation interfaces can inadvertently provide adversaries with an expanded privacy-related attack surfaces. Recent studies show that advanced membership-inference attacks succeed by exploiting confidence-drop trajectories, induced through attribution-guided perturbations, as discriminative features, rather than directly using confidence scores or explanation vectors. Existing defenses against membership inference fail to directly mitig",
  "authors": "Varun Sharma, Kar Wai Fok, Vrizlynn L. L. Thing",
  "category": "research",
  "topics": "bias-fairness,privacy-surveillance,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-03T02:59:53.000Z",
  "fetched_at": "2026-07-14T14:14:24.249Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/298",
  "original_url": "https://arxiv.org/abs/2607.02903v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}