Michael-Andrei Panaitescu-Liess
6 papers · 2021–2026 · 4 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐บ๏ธ
Taxonomy Completionist
(11)
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
adversarial attack
(2)
copyright infringement
(2)
large language model
(2)
federated learning
(2)
backdoor attack
(2)
poisoning attack
(1)
vision-language model
(1)
context inference
(1)
membership inference
(1)
zero-shot classification
(1)
membership inference attack
(1)
spurious feature
(1)
content generation
(1)
training data extraction
(1)
large language model alignment
(1)
group robustness
(1)
adversarial fine-tuning
(1)
reinforcement learning human feedback
(1)
model compression
(1)
minority sample
(1)
Papers
AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment
AAAI 2026
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
AAAI 2025
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
NAACL 2025
Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
ICLR 2024
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
ICLR 2024
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes
NeurIPS 2021