Patrick McDaniel
5 papers · 2018–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
๐ฃ Hot Topic Early Bird ๐ Academic Marathon ยท Sprint ๐ Conference Polyglot ยท Bronze ๐ Interdisciplinary Bridge ยท Bronze ๐งญ Keyword Pioneer
๐
Conference Pioneer
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
large language model
(2)
model robustness
(1)
adversarial training
(1)
intellectual property
(1)
safety alignment
(1)
black-box attack
(1)
ensemble method
(1)
watermark detection
(1)
jailbreak attack
(1)
fine-tuning attack
(1)
jailbreak defense
(1)
transfer attack
(1)
agent system
(1)
model extraction
(1)
backdoor trigger
(1)
threshold adaptation
(1)
prefixed safety
(1)
adversarial robustness
(1)
infringement detection
(1)
Papers
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
ICLR 2025
Can Watermarks be Used to Detect LLM IP Infringement For Free?
ICLR 2025
On the Robustness Tradeoff in Fine-Tuning
ICCV 2025
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
NeurIPS 2024
Ensemble Adversarial Training: Attacks and Defenses
ICLR 2018