{"data":{"id":"7e31d60d-29c0-4f0a-8d50-4b9601aa4e69","title":"Backdoor-Based Watermarking in Multi-Client Split Learning","summary":"Split learning (SL, a technique where a deep neural network is divided between a client's local computer and a server to reduce computation on the client side) faces challenges in protecting intellectual property through watermarking (a hidden mark added to prove ownership) in multi-client settings, because the server can erase watermarks, later clients can overwrite earlier ones, and malicious clients can deliberately remove them. This paper proposes MarkSplit and MarkSplit+, two methods that embed watermarks more robustly by jointly training the main task with watermark samples in a three-tiered training structure, with MarkSplit+ using dynamic adjustment for adversarial environments with malicious participants.","solution":"The source proposes two explicit methods: (1) MarkSplit for benign environments, which jointly trains main-task and watermark samples within a three-tiered structure (mini-local, local, and global rounds); and (2) MarkSplit+ for adversarial settings, which enhances robustness by dynamically adjusting watermark sample counts per client based on watermark detection accuracy. Both use a watermark sample generation technique called Color-Shape-ID.","labels":["research","security"],"sourceUrl":"http://ieeexplore.ieee.org/document/11602638","publishedAt":"2026-07-09T13:18:51.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning"],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-07-09T13:18:51.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.85,"researchCategory":"peer_reviewed","atlasIds":null}}