Fabio Roli
6 papers · 2006–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (19) π Interdisciplinary Bridge π Cross-Pollinator (12)
π£
Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(14)
π§¬
Topic Evolution
β
The Questioner
π
Trend Setter
Conferences
AAAI (2)
NIPS (2)
ICML (1)
JMLR (1)
Top co-authors
Keywords
gradient-based attack
(3)
adversarial example
(2)
robustness evaluation
(2)
feature selection
(1)
model robustness
(1)
adversarial machine learning
(1)
safety alignment
(1)
text categorization
(1)
malware detection
(1)
adversarial attack
(1)
decision boundary
(1)
mechanistic interpretability
(1)
model ablation
(1)
attack evaluation
(1)
optical character recognition
(1)
self-organizing map
(1)
training data poisoning
(1)
image text extraction
(1)
refusal suppression
(1)
attack optimization
(1)
Papers
SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models
AAAI 2026
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
AAAI 2025
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
NIPS 2022
Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
NIPS 2021
Is Feature Selection Secure against Training Data Poisoning?
ICML 2015
Spam Filtering Based On The Analysis Of Text Information Embedded Into Images
JMLR 2006