Scholar
Lorenzo Cavallaro
Google Scholar ID: oWT7fIYAAAAJ
University College London
Systems Security
Adversarial Machine Learning
AI Security
Trustworthy Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
5,314
H-index
29
i10-index
53
Publications
20
Co-authors
1
list available
Publications
24 items
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
2026
Cited
0
Breaking Windows Malware Detection: A Comprehensive Evaluation of Problem-Space Adversarial Robustness
2026
Cited
0
REPLICANT: Learning Policies for Evading and Hardening Malware Detectors
2026
Cited
0
Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios
2026
Cited
0
Malaika: Understanding Malware through Tri-Grounded Agentic Reasoning
2026
Cited
0
Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning
2026
Cited
0
Demystifying the Mythos or Disrupting Bugonomics? From Zero-Day Asymmetry to Defender Remediation Throughput
2026
Cited
0
Reading Calibrated Uncertainty from Language Model Trajectories
2026
Cited
0
Load more
Co-authors
1 total
Andrea Lanzi
Associate Professor at Department Computer Science at University of Milan
