Yigitcan Kaya
9 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (10) π§ Keyword Pioneer π Conference Polyglot (4)
π
Academic Marathon
(6)
π
Cross-Pollinator
(13)
π
Triple Crown
β
The Questioner
(2)
Conferences
ICLR (4)
ICML (3)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
adversarial attack
(3)
federated learning
(1)
image classification
(1)
data poisoning
(1)
data augmentation
(1)
neural network optimization
(1)
early exit
(1)
distribution matching
(1)
backdoor attack
(1)
deep neural network
(1)
evasion attack
(1)
adversarial example
(1)
inference efficiency
(1)
security evaluation
(1)
statistical detection
(1)
membership inference attack
(1)
content generation
(1)
adaptive attack
(1)
copyright infringement
(1)
large language model
(1)
Papers
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
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
ICLR 2024
Generating Distributional Adversarial Examples to Evade Statistical Detectors
ICML 2022
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes
NIPS 2021
When Does Data Augmentation Help With Membership Inference Attacks?
ICML 2021
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
ICLR 2021
How to 0wn the NAS in Your Spare Time
ICLR 2020
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
ICML 2019