FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs

no code implementations • 12 Dec 2023 • Swanand Ravindra Kadhe, Anisa Halimi, Ambrish Rawat, Nathalie Baracaldo

We evaluate the performance-fairness trade-off for SISA, and empirically demsontrate that SISA can indeed reduce fairness in LLMs.

Fairness Unsupervised Pre-training

Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks

no code implementations • 7 Dec 2023 • Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou, Ling Cai, Nathalie Baracaldo

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs. It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs through poisoning attacks aimed at generating undesirable outputs.

Data Poisoning object-detection +2

Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection

no code implementations • 30 Oct 2023 • Swanand Ravindra Kadhe, Heiko Ludwig, Nathalie Baracaldo, Alan King, Yi Zhou, Keith Houck, Ambrish Rawat, Mark Purcell, Naoise Holohan, Mikio Takeuchi, Ryo Kawahara, Nir Drucker, Hayim Shaul, Eyal Kushnir, Omri Soceanu

The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and its partner banks.

Anomaly Detection Federated Learning +1