Picture for Quazi Mishkatul Alam

Quazi Mishkatul Alam

Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment

Add code
Feb 21, 2025
Viaarxiv icon

Fool the Hydra: Adversarial Attacks against Multi-view Object Detection Systems

Add code
Nov 30, 2023
Viaarxiv icon

Attention Deficit is Ordered! Fooling Deformable Vision Transformers with Collaborative Adversarial Patches

Add code
Nov 21, 2023
Viaarxiv icon

Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics

Add code
Jul 25, 2023
Figure 1 for Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics
Figure 2 for Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics
Figure 3 for Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics
Figure 4 for Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics
Viaarxiv icon

DeepMem: ML Models as storage channels and their applications

Add code
Jul 24, 2023
Figure 1 for DeepMem: ML Models as storage channels and their applications
Figure 2 for DeepMem: ML Models as storage channels and their applications
Figure 3 for DeepMem: ML Models as storage channels and their applications
Figure 4 for DeepMem: ML Models as storage channels and their applications
Viaarxiv icon