CORTEXA
← Browse
arxivcs.LGcs.CR2026-07-07

Auditing of Unlearning Algorithms

Sahasrajit Sarmasarkar, Anastasia Koloskova, Sanmi Koyejo

Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge. We propose a practical auditor that computes data-dependent lower bounds on the unlearning parameter $\varepsilon$ using membership inference attacks. Evaluating multiple unlearning algorithms, we find a sharp separation: algorithms with rigorous guarantees, such as model clipping and rewind-to-delete, achieve very small $\varepsilon$ bounds that do not falsify their unlearning guarantees, whereas empirical methods such as Hessian-based unlearning, interleaved ascent-descent, ascent on the forget set, and fine-tuning on the retain set exhibit large bounds, indicating poor unlearning. Our auditor provides a practical tool for empirically falsifying unlearning claims through a hypothesis-testing framework, and we validate it on CIFAR-100 and Shakespeare text.

View free PDFSource page

Related papers

arxivcs.CRcs.LG2026-07-23

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification

Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova, Akira Takahashi, Antigoni Polychroniadou, Nicolas Papernot

Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data. This makes them especially attractive for auditing models deployed in sensitive domains such as…

View free PDFSource page
arxivcs.LGcs.ARcs.CR2026-07-26

ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection At Scale

Yaroslav Popryho, Debjit Pal, Inna Partin-Vaisband

Modern System-on-Chip (SoCs) often contain hundreds of millions to tens of billions of gates, making existing Hardware Trojan (HT) detection methods impractical due to their immense scale. The proposed approach incorporates symbolically enabled learning by modeling flattened gate…

View free PDFSource page
arxivcs.CRcs.CLcs.LG2026-07-23

Adversarial Prompts for Acceptance Collapse in Speculative Decoding

Run Wang, Chaoyi Zhou, Xi Liu, Yi Zhu, Amir Salarpour, Pedram MohajerAnsari, et al.

Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model. However, this guarantee of semantic equivalence masks a severe operational vulnerability: draft-targ…

View free PDFSource page
arxivcs.LGcs.CRcs.CVcs.MM2026-07-23

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection

Othmane Harraq, Tamer Aldwairi

Talking-face (TF) deepfake generation synthesizes photore- alistic facial video from a static source image and an au- dio signal, producing forgeries that current image-based detectors consistently fail to identify. Unlike face-swap ma- nipulation, TF synthesis has no underlying…

View free PDFSource page
arxivcs.LGcs.AIcs.CRcs.CVstat.ML2026-07-23

Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

Vishnu Bindu Balachandran

Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized Pólya urn, we prove almost-sure convergence to a mean-field equilibrium whose s…

View free PDFSource page