Awesome Multimodal
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Matt Fredrikson — most-cited papers & profile · Multimodal
← authors
·
overview
Matt Fredrikson
7
papers ·
83
citations ·
0
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
The Limitations of Deep Learning in Adversarial Settings
2015 · 72 citations
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
2017 · 11 citations
A New Framework for Cybersecurity Refusals in AI Agents
2026
SecCodePRM: A Process Reward Model for Code Security
2026
A Mixture of Linear Corrections Generates Secure Code
2025
D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
2025
Faithful Explanations for Deep Graph Models
2022
Topics
Adversarial ML
LLM Security
Vulnerability Detection
Network Security
Code Generation
Code Models
Bug Detection
Software Engineering
Evaluation
Safety & Alignment