Ching-yu Kao

13 papers A* 1A 2C 1Journal 4Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents.
CoRR
Ching-yu Kao, Xinfeng Li, Shenyu Dai, Tianze Qiu, Pengcheng Zhou, Eric Hanchen Jiang, Philip Sperl
2025 A conf
GRASPED: Graph Anomaly Detection Using Autoencoder with Spectral Encoder and Decoder.
ECAI
Wei Herng Choong, Jixing Liu, Ching-yu Kao, Philip Sperl
2025 J jnl
GRASPED: Graph Anomaly Detection using Autoencoder with Spectral Encoder and Decoder (Full Version).
CoRR
Wei Herng Choong, Jixing Liu, Ching-yu Kao, Philip Sperl
2025 — conf
Using LLMs to Identify Personal Data Processing in Source Code.
SP (Workshops)
Immanuel Kunz, Ching-yu Kao, Daniel Kowatsch, Jens Hiller, Julian Schütte, Dmitry Prokhorenkov, Konstantin Böttinger
2024 — conf
Near Real-Time Detection and Rectification of Adversarial Patches.
FICC (2)
Ching-yu Kao, Iheb Ghanmi, Houcemeddine Ben Ayed, Ayush Kumar, Konstantin Böttinger
2022 — conf
Comparing Unsupervised Detection Algorithms for Audio Adversarial Examples.
SPECOM
Shanatip Choosaksakunwiboon, Karla Pizzi, Ching-yu Kao
2022 C conf
Real or Fake? A Practical Method for Detecting Tempered Images.
IPAS
Ching-yu Kao, Hongjia Wan, Karla Markert, Konstantin Böttinger
2022 — conf
Rectifying adversarial inputs using XAI techniques.
EUSIPCO
Ching-yu Kao, Junhao Chen, Karla Markert, Konstantin Böttinger
2022 J jnl
Visualizing Automatic Speech Recognition - Means for a Better Understanding?
CoRR
Karla Markert, Romain Parracone, Mykhailo Kulakov, Philip Sperl, Ching-yu Kao, Konstantin Böttinger
2020 A conf
DLA: Dense-Layer-Analysis for Adversarial Example Detection.
EuroS&P
Philip Sperl, Ching-yu Kao, Peng Chen, Xiao Lei, Konstantin Böttinger
2019 — conf
Clear Sanctions, Vague Rewards: How China's Social Credit System Currently Defines "Good" and "Bad" Behavior.
FAT
Severin Engelmann, Mo Chen, Felix Fischer, Ching-yu Kao, Jens Grossklags
2019 J jnl
DLA: Dense-Layer-Analysis for Adversarial Example Detection.
CoRR
Philip Sperl, Ching-yu Kao, Peng Chen, Konstantin Böttinger
2019 A* conf
Stack Overflow Considered Helpful! Deep Learning Security Nudges Towards Stronger Cryptography.
USENIX Security Symposium
Felix Fischer, Huang Xiao, Ching-yu Kao, Yannick Stachelscheid, Benjamin Johnson, Danial Razar, Paul Fawkesley, Nat Buckley, Konstantin Böttinger, Paul Muntean, Jens Grossklags