Jianshuo Dong
4 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
π
Cross-Pollinator
(15)
Conferences
ACL (1)
EMNLP (1)
ICCV (1)
ICLR (1)
Top co-authors
Research topics
Keywords
model security
(1)
neural network security
(1)
data augmentation
(1)
instruction following
(1)
intent detection
(1)
adversarial attack
(1)
hidden state
(1)
linear probing
(1)
model internal
(1)
probing classifier
(1)
large language model
(1)
bit flip attack
(1)
linear probe
(1)
prompt leakage
(1)
reliability evaluation
(1)
quantized model
(1)
nuance-oriented reliability
(1)
Papers
Revisiting the Reliability of Language Models in Instruction-Following
ACL 2026
βIβve Decided to Leakβ: Probing Internals Behind Prompt Leakage Intents
EMNLP 2025
An Engorgio Prompt Makes Large Language Model Babble on
ICLR 2025
One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
ICCV 2023