Michael Backes
27 papers · 2019–2026 · 10 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 ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (50) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Gold 🌉 Interdisciplinary Bridge · Gold 🐣 Hot Topic Early Bird
👥
Mega-Team · Legion
🏆
Keyword Champion
(2)
🤝
Dynamic Duo
(20)
👑
Triple Crown
⚡
Prolific Year · Productive
❓
The Questioner
(3)
💎
Century Club · Bronze
🌈
Renaissance Researcher
(6)
🗃️
Keyword Collector
(131)
Venues
Top co-authors
Research topics
Machine Learning
(18)
Artificial Intelligence
(17)
Core AI
(17)
Application Areas
(13)
Deep Learning
(9)
Learning Types · Machine Learning
(9)
Core Methods
(5)
Learning Types · Deep Learning
(5)
Computer Vision
(4)
Natural Language Processing
(4)
Models
(4)
Resources & Methods
(4)
Security & Privacy
(3)
Architectures
(3)
Computer Science
(2)
Keywords
large language model
(9)
adversarial attack
(5)
self-supervised learning
(3)
security vulnerability
(3)
diffusion model
(3)
generative model
(2)
representation learning
(2)
prompt injection
(2)
defense mechanism
(2)
data poisoning
(2)
differential privacy
(2)
image generation
(2)
vision-language model
(2)
model robustness
(1)
vision transformer
(1)
graph classification
(1)
text classification
(1)
contrastive learning
(1)
robustness
(1)
multimodal learning
(1)
Papers
DE-CLIP: Few-Shot Anomaly Detection via Difference-Guided Embedding Editing
ACL 2026
Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services
ACL 2026
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
ACL 2026
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
CVPR 2026
Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media
ACL 2025
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
EMNLP 2025
Captured by Captions: On Memorization and its Mitigation in CLIP Models
ICLR 2025
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
ICML 2025
Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
ICCV 2025
JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
ACL 2025
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
ICML 2025
SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
ICLR 2025
When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs
ACL 2025
Composite Backdoor Attacks Against Large Language Models
NAACL 2024
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
WACV 2024
Localizing Memorization in SSL Vision Encoders
NeurIPS 2024
Memorization in Self-Supervised Learning Improves Downstream Generalization
ICLR 2024
ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities
EMNLP 2024
Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
NeurIPS 2024
Position: TrustLLM: Trustworthiness in Large Language Models
ICML 2024
Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models
EMNLP 2024
The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective
EMNLP 2024
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
CVPR 2023
Data Poisoning Attacks Against Multimodal Encoders
ICML 2023
Generated Graph Detection
ICML 2023
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
ICLR 2023
Fairwalk: Towards Fair Graph Embedding
IJCAI 2019