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.LG2026-07-07

POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking

Zhangheng LI, Jianing Zhu, Junyuan Hong, Sungmin Eum, Shuowen Hu, Suya You, et al.

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sensitive examples could be unintentionally encoded, raising concerns about privacy or copyright violat…

View free PDFSource page
arxivcs.CRcs.LG2026-07-17

Code-Poisoning Property Inference Attacks

Xukun Luan, Yuhui Gong, Gang Zhang, Zixuan Huang, Yuanguo Bi, Xuesong Li, et al.

The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning (ML) models using available code quickly. The training data for ML models, often regarded as private property (e.g., clinical records, transaction i…

View free PDFSource page
arxivcs.CRcs.CVcs.LG2026-07-17

Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents

Halima Bouzidi, Mboutidem Ekemini Mkpong, Mohammad Abdullah Al Faruque

Multimodal AI agents increasingly rely on persistent long-term memory to ground generation in past visual and textual episodes. We show that unconditional trust in visual data creates a critical vulnerability. We propose Lucid, a black-box adversarial framework that compromises m…

View free PDFSource page
arxivcs.CRcs.AIcs.LG2026-07-22

Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection

Shrinidhi Sridhar, Vikas K. Malviya

An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices. But there is a trade-off between security and energy use, as strong detection models can drain the battery of devices fast. This work tests different Multi-Layer Pe…

View free PDFSource page
arxivcs.CRcs.AIcs.LG2026-07-17

Boundary-Seeking GAN-Augmented TabTransformer for Adversarially Robust Intrusion Detection

Raihan Sultan Pasha Basuki, Aliyah Kurniasih

Machine learning-based intrusion detection systems (IDSs) often suffer from class imbalance and vulnerability to adversarial attacks, leading to degraded detection performance and reduced robustness. This study proposes a TabTransformer framework augmented by the Boundary-Seeking…

View free PDFSource page