117 results on '"Michael Backes"'
Search Results
2. Vera Verto: Multimodal Hijacking Attack.
3. Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution.
4. ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization.
5. Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification.
6. SOS! Soft Prompt Attack Against Open-Source Large Language Models.
7. TrustLLM: Trustworthiness in Large Language Models.
8. Link Stealing Attacks Against Inductive Graph Neural Networks.
9. Memorization in Self-Supervised Learning Improves Downstream Generalization.
10. Conversation Reconstruction Attack Against GPT Models.
11. Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization.
12. Do You Even Lift? Strengthening Compiler Security Guarantees Against Spectre Attacks.
13. Comprehensive Assessment of Jailbreak Attacks Against LLMs.
14. Voice Jailbreak Attacks Against GPT-4o.
15. UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images.
16. Efficient Data-Free Model Stealing with Label Diversity.
17. FAKEPCD: Fake Point Cloud Detection via Source Attribution.
18. You Are How You Walk: Quantifying Privacy Risks in Step Count Data.
19. Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models.
20. Composite Backdoor Attacks Against Large Language Models.
21. Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis.
22. Generated Graph Detection.
23. Watermarking Diffusion Model.
24. Secure Composition of Robust and Optimising Compilers.
25. MGTBench: Benchmarking Machine-Generated Text Detection.
26. In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT.
27. Prompt Stealing Attacks Against Text-to-Image Generation Models.
28. FACE-AUDITOR: Data Auditing in Facial Recognition Systems.
29. Two-in-One: A Model Hijacking Attack Against Text Generation Models.
30. Generating Less Certain Adversarial Examples Improves Robust Generalization.
31. Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing.
32. Vision-language models boost food composition compilation.
33. On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts.
34. Comprehensive Assessment of Toxicity in ChatGPT.
35. Provably Robust Cost-Sensitive Learning via Randomized Smoothing.
36. Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models.
37. Transferable Availability Poisoning Attacks.
38. Revisiting Transferable Adversarial Image Examples: Attack Categorization, Evaluation Guidelines, and New Insights.
39. Backdoor Attacks Against Dataset Distillation.
40. Quantifying Privacy Risks of Prompts in Visual Prompt Learning.
41. SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models.
42. Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models.
43. Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning.
44. Prompt Backdoors in Visual Prompt Learning.
45. From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need.
46. 'Do Anything Now': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.
47. Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots.
48. Data Poisoning Attacks Against Multimodal Encoders.
49. A Systematic Study of the Consistency of Two-Factor Authentication User Journeys on Top-Ranked Websites (Extended Version).
50. On Xing Tian and the Perseverance of Anti-China Sentiment Online.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.