Search Results for author:
Found 12 papers, 2 papers with code
May the Noise be with you: Adversarial Training without Adversarial Examples
We model the propagation of noise through the layers, introducing a closed-form stochastic loss function that encapsulates a noise variance parameter.
Fool the Hydra: Adversarial Attacks against Multi-view Object Detection Systems
Adversarial patches exemplify the tangible manifestation of the threat posed by adversarial attacks on Machine Learning (ML) models in real-world scenarios.
Attention Deficit is Ordered! Fooling Deformable Vision Transformers with Collaborative Adversarial Patches
The latest generation of transformer-based vision models has proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attributed to their remarkable prowess in relation modeling.
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks
Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows.
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
Specifically, we develop cross-modality attacks on alignment where we pair adversarial images going through the vision encoder with textual prompts to break the alignment of the language model.
Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics
In this paper, we introduce LtC, a collaborative framework between the video source and the analytics server, that efficiently learns to reduce the video streams within an analytics pipeline.
DeepMem: ML Models as storage channels and their (mis-)applications
In this paper, we propose a novel information theoretic perspective of the problem; we consider the ML model as a storage channel with a capacity that increases with overparameterization.
Jedi: Entropy-based Localization and Removal of Adversarial Patches
Jedi tackles the patch localization problem from an information theory perspective; leverages two new ideas: (1) it improves the identification of potential patch regions using entropy analysis: we show that the entropy of adversarial patches is high, even in naturalistic patches; and (2) it improves the localization of adversarial patches, using an autoencoder that is able to complete patch regions from high entropy kernels.
ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints
Thus, we propose ROOM, a novel Real-time Online-Offline attack construction Model where an offline component serves to warm up the online algorithm, making it possible to generate highly successful attacks under time constraints.
Securing Connected Vehicle Applications with an Efficient Dual Cyber-Physical Blockchain Framework
While connected vehicle (CV) applications have the potential to revolutionize traditional transportation system, cyber and physical attacks on them could be devastating.
Cryptography and Security
Defensive Approximation: Securing CNNs using Approximate Computing
We show that our approximate computing implementation achieves robustness across a wide range of attack scenarios.
Spectre Returns! Speculation Attacks using the Return Stack Buffer
In particular, on Core-i7 Skylake and newer processors (but not on Intel's Xeon processor line), a patch called RSB refilling is used to address a vulnerability when the RSB underfills; this defense interferes with SpectreRSB's ability to launch attacks that switch into the kernel.
Cryptography and Security
