Zhenting Wang
28 papers · 2022–2026 · 9 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 ↓+7 more ↓ Show less ↑
π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (43) π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π€ Dynamic Duo (14)
π€
Dynamic Duo
(14)
π
Renaissance Researcher
(6)
π₯
Unstoppable Β· Bronze
β
The Questioner
(4)
β‘
Prolific Year Β· Prolific
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(143)
Top co-authors
Research topics
Artificial Intelligence
(20)
Core AI
(20)
Machine Learning
(16)
Deep Learning
(15)
Learning Types Β· Machine Learning
(10)
Learning Types Β· Deep Learning
(8)
Application Areas
(7)
Natural Language Processing
(6)
Models
(6)
Resources & Methods
(5)
Security & Privacy
(4)
Privacy
(4)
Techniques
(4)
Computer Vision
(3)
Computer Science
(2)
Keywords
backdoor attack
(7)
large language model
(5)
adversarial attack
(4)
neural network
(4)
trojan attack
(3)
neural network security
(3)
adversarial learning
(3)
image classification
(2)
backdoor defense
(2)
generative model
(2)
reverse engineering
(2)
model security
(2)
backdoor detection
(2)
trigger inversion
(2)
deep neural network
(2)
chain-of-thought reasoning
(2)
multimodal large language model
(2)
in-context learning
(1)
self-supervised learning
(1)
preference learning
(1)
Papers
Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening
WACV 2026
Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
ACL 2026
Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
CVPR 2025
ADO: Automatic Data Optimization for Inputs in LLM Prompts
ACL 2025
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
ICLR 2025
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
NAACL 2025
CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
CVPR 2025
Data-centric NLP Backdoor Defense from the Lens of Memorization
NAACL 2025
EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
NAACL 2025
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
COLING 2025
How to Evaluate and Mitigate IP Infringement in Visual Generative AI?
ICML 2025
Invisible Backdoor Attack against Self-supervised Learning
CVPR 2025
LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
ICLR 2025
MLLM-as-a-Judge for Image Safety without Human Labeling
CVPR 2025
ProSec: Fortifying Code LLMs with Proactive Security Alignment
ICML 2025
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering
ICML 2025
Token-Budget-Aware LLM Reasoning
ACL 2025
Visual Agents as Fast and Slow Thinkers
ICLR 2025
DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
ICLR 2024
Finding a needle in a haystack: A Black-Box Approach to Invisible Watermark Detection
ECCV 2024
How to Trace Latent Generative Model Generated Images without Artificial Watermark?
ICML 2024
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
ACL 2023
UNICORN: A Unified Backdoor Trigger Inversion Framework
ICLR 2023
Where Did I Come From? Origin Attribution of AI-Generated Images
NeurIPS 2023
BppAttack: Stealthy and Efficient Trojan Attacks Against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
CVPR 2022
Complex Backdoor Detection by Symmetric Feature Differencing
CVPR 2022
Rethinking the Reverse-engineering of Trojan Triggers
NeurIPS 2022
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
NeurIPS 2022