Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
1 version
DW
David Wagner
cs.CRcs.LGcs.AIcs.CVcs.CLstat.MLcs.SIcs.CYHistory of NursingHope
On Valency
published · living versionsPreprints & journals
43 papers in the corpus · 1980–2025Towards Better Attribute Inference Vulnerability Measures
0 citations
Semantic-Aware Parsing for Security Logs
0 citations
JULI: Jailbreak Large Language Models by Self-Introspection
0 citations
Certifiably Robust RAG against Retrieval Corruption
7 citations
Towards more accurate and useful data anonymity vulnerability measures
2 citations
Generative AI Security: Challenges and Countermeasures
9 citations
PAL: Proxy-Guided Black-Box Attack on Large Language Models
6 citations
Jatmo: Prompt Injection Defense by Task-Specific Finetuning
54 citations
Mark My Words: Analyzing and Evaluating Language Model Watermarks
7 citations
Can LLMs Follow Simple Rules?
3 citations
PubDef: Defending Against Transfer Attacks From Public Models
0 citations
Continuous Learning for Android Malware Detection
23 citations
Editorial.
1 citation
REAP: A Large-Scale Realistic Adversarial Patch Benchmark
25 citations
Part-Based Models Improve Adversarial Robustness
4 citations
SLIP: Self-supervision meets Language-Image Pre-training
285 citations
Hopper: Modeling and Detecting Lateral Movement (Extended Report)
1 citation
Learning Security Classifiers with Verified Global Robustness Properties
27 citations
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
9 citations
Model-Agnostic Defense for Lane Detection against Adversarial Attack
9 citations
Editorial.
2 citations
Mathematics education in a time of crisis-a viral pandemic.
39 citations
Tensions and Hopes for Embedding Peace and Sustainability in Science Education: Stories from Science Textbook Authors.
10 citations
Adversarial Examples for -Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams
5 citations
A Large-Scale Analysis of Attacker Activity in Compromised Enterprise Accounts
1 citation
Minority Reports Defense: Defending Against Adversarial Patches
49 citations
SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing
21 citations
Minimum-Norm Adversarial Examples on KNN and KNN-Based Models
23 citations
What can we do against racism in mathematics education research?
20 citations
Pandemic: lessons for today and tomorrow?
147 citations
Detecting and Characterizing Lateral Phishing at Scale
63 citations
Stateful Detection of Black-Box Adversarial Attacks
116 citations
Defending Against Adversarial Examples with K-Nearest Neighbor
15 citations
On the Robustness of Deep K-Nearest Neighbors
52 citations
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
2,171 citations
Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
1,070 citations
MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
154 citations
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
357 citations
The Feasibility of Dynamically Granted Permissions: Aligning Mobile Privacy with User Preferences
131 citations
Towards Evaluating the Robustness of Neural Networks
8,844 citations
Spoofing 2D Face Detection: Machines See People Who Aren't There
1 citation
Defensive Distillation is Not Robust to Adversarial Examples
222 citations
The proletarianization of nursing in the United States.
29 citations
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.