Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning
Fairis introduces fairness-aware aggregation with provable influence bounds for collaborative ML among financial institutions, defending against adversarial clients who deliberately degrade group fairness.
Summary written by editorial AI · Source link below
arXiv:2608.06469v1 Announce Type: new Abstract: Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation. Existing fairness-aware aggregation methods remain formally vulnerable to fairness poisoning: a malicious client maximizing group disparity while preserving accuracy evades accuracy-based Byzantine defenses, and in our threat model FairFed's gap-based weighting can be gamed by an adversary who observes the glo
Editorial Analysis
Financial institutions engaging in collaborative ML face both regulatory fairness obligations and adversarial manipulation risks; provable containment of poisoning influence addresses both concerns simultaneously.
Evaluate fairness-poisoning resilience in any collaborative ML arrangement with external partners, especially under DORA and EU anti-discrimination mandates.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI admits it didn't disclose rogue AI wiki hijacking incident2d
- Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel3d
- Using a VM to Contain an AI Agent3d
- Companies Have 6 Months to Prepare for Automated Attacks3d
- [NEU] [mittel] Ollama: Schwachstelle ermöglicht Offenlegung von Informationen3d