FogFool creates fog-based adversarial perturbations using Perlin noise optimization to achieve high black-box transferability (83.74% TASR) and robustness to defenses in remote sensing classification.
Adversarial examples in the physical world
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
INTARG generates effective real-time adversarial attacks on time-series regression models by selectively targeting high-confidence high-error steps in a bounded-buffer online setting, increasing prediction error up to 2.42x while attacking under 10% of timesteps.
SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.
A reinforcement learning attacker manipulates client sensor observations in federated learning to induce repetitive server memory updates, achieving around 70% repeated update rate and enabling remote Rowhammer bit flips on an automatic speech recognition model.
Experiments with around 2200 variations show that shallower networks with reduced features and ReLU activation reduce adversarial vulnerability in ML-NIDS and outperform deeper adversarially trained models while keeping high clean-data performance.
citing papers explorer
-
Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
FogFool creates fog-based adversarial perturbations using Perlin noise optimization to achieve high black-box transferability (83.74% TASR) and robustness to defenses in remote sensing classification.
-
INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression
INTARG generates effective real-time adversarial attacks on time-series regression models by selectively targeting high-confidence high-error steps in a bounded-buffer online setting, increasing prediction error up to 2.42x while attacking under 10% of timesteps.
-
LLM-Agnostic Semantic Representation Attack
SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.
-
Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients
A reinforcement learning attacker manipulates client sensor observations in federated learning to induce repetitive server memory updates, achieving around 70% repeated update rate and enabling remote Rowhammer bit flips on an automatic speech recognition model.
-
A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
Experiments with around 2200 variations show that shallower networks with reduced features and ReLU activation reduce adversarial vulnerability in ML-NIDS and outperform deeper adversarially trained models while keeping high clean-data performance.