all InfoSec news
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
April 15, 2024, 4:10 a.m. | Yanting Wang, Wei Zou, Jinyuan Jia
cs.CR updates on arXiv.org arxiv.org
Abstract: Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support samples) for a classification task. However, an attacker could perform data poisoning attacks by manipulating some support samples such that the classifier makes the attacker-desired, arbitrary prediction for a testing input. Empirical defenses cannot provide formal robustness guarantees, leading to a cat-and-mouse game between the attacker and defender. Existing certified defenses …
arxiv attacker attacks build called classification cs.cr data data poisoning foundation foundation models palm poisoning poisoning attacks support task training
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Information Security Engineer - Vulnerability Management
@ Starling Bank | Southampton, England, United Kingdom
Manager Cybersecurity
@ Sia Partners | Rotterdam, Netherlands
Compliance Analyst
@ SiteMinder | Manila
Information System Security Engineer (ISSE)-Level 3, OS&CI Job #447
@ Allen Integrated Solutions | Chantilly, Virginia, United States
Enterprise Cyber Security Analyst – Advisory and Consulting
@ Ford Motor Company | Mexico City, MEX, Mexico