PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

AI deep dive: Data bias

bugcrowd.com | research | #ai-security | #bugcrowd | #machine-learning | #data-bias | #fairness | #responsible-ai
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Using Amazon's discriminatory AI hiring tool as an example, Bugcrowd explains AI data bias: its definition, representation and pre-existing bias types, and deployer responsibility.
Published
Collected

Related coverage

blog · bugcrowd.com
AI lectures with Dr. Brumley Part 3 | Securing the AI attack surface
Part three of Bugcrowd's AI lecture series with Dr. Brumley maps AI threats along three axes — knowledge, position and goal — and surveys classical ML attacks and recent LLM-era incidents.
blog · bugcrowd.com
AI lectures with Dr. Brumley Part 1 | Defining AI for CISOs
Bugcrowd's Dr. David Brumley opens his AI lecture series for CISOs by breaking 'AI' into seven distinct mechanisms — from machine learning to symbolic reasoning — each with its own attack surface.
research · blog.quarkslab.com
Weisfeiler-Lehman Graph Kernel for Binary Function Analysis
A method applying the Weisfeiler-Lehman graph kernel to control-flow graphs, comparing binary functions against large known-function databases for classification, clustering and near-duplicate detection.
research · xbow.com
Machine Learning for Vulnerability Discovery
Machine learning accelerates vulnerability discovery but over-reports false positives without runtime context; the article argues for pairing ML detection with AI-driven exploitability validation.
research · vercel.com
Everything hackable will get hacked
Open-weight models that allow perform offensive research present an emerging cybersecurity challenge. But you do not need to wait for specialized models to begin defensive cybersecurity work.
research · vercel.com
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilities
Today we're releasing DeepsecBench, a benchmark that evaluates how well different models find security vulnerabilities in application code.
Back