PGD
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models
arXiv:2605.25889v4 Announce Type: replace Abstract: Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations: a $16/255$ PGD attack drops OpenVLA-7B's LIBERO success from $95\%$ to under $5\%$. Whether this trade-off has a theoretical floor was open. We prove that it does. For any VLA policy, capability $I(\Astar;\Api)$ and robustness $I(\Api;\Atildepi)-I(\Api;\delta)$ sum to at most $H(\Astar)+I(X;\Xtilde)$, the task...
Ghost: Plausible Yet Unlearnable Trajectories via On-Manifold Substitution for Next-POI Privacy
arXiv:2606.03711v1 Announce Type: new Abstract: A publisher who releases check-in trajectories inadvertently publishes a strong predictor of every user's future locations. We address this risk by generating unlearnable trajectories, perturbed sequences that yield victim models with degraded next-Point-of-Interest (next-POI) accuracy on clean test inputs. Direct ports of image-domain unlearnable examples fail on two counts.
SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
Announce Type: replace Abstract: Continual learning under adversarial conditions remains an open problem, as existing methods often compromise either robustness, scalability, or both. We propose a novel framework that integrates Interval Bound Propagation (IBP) with a hypernetwork-based architecture to enable certifiably robust continual learning across sequential tasks. Our method, SHIELD, generates task-specific model parameters via a shared hypernetwork conditioned solely on compact task...
The Security Budget of Code LLMs: An Information-Theoretic Capacity-Security Bound
Announce Type: new Abstract: AI programming assistants make natural-language prompts a software-development interface, so small prompt perturbations become usability and security risks. We study an information-theoretic trade-off for code LLMs between functional capacity, $\Cap=\rmI(c^*;c_\pi)$, and perturbation retention, $\Sec=\rmI(c_\pi;\tilde c_\pi)$. Here $\Sec$ is a retention-channel quantity, not a direct measure of exploit success or vulnerable-code generation. For code completion...
Weighted Sum-Rate Enhancement for Flexible Intelligent Metasurface-Assisted Multicell Systems
arXiv:2606.06845v1 Announce Type: new Abstract: Flexible intelligent metasurface (FIM) technology has emerged as a promising technology for enhancing wireless communication performance by dynamically reshaping the propagation environment. Compared with conventional rigid reconfigurable intelligent surfaces (RIS), an FIM is composed of multiple electromagnetic (EM) scattering units, each of which can flexibly modify its displacement in the direction normal to the surface, thereby...
The Security Budget of Code LLMs: An Information-Theoretic Capacity-Security Bound
arXiv:2606.03308v2 Announce Type: replace Abstract: AI programming assistants make natural-language prompts a software-development interface, so small prompt perturbations become usability and security risks. We study an information-theoretic trade-off for code LLMs between functional capacity, $\Cap=\rmI(c^*;c_\pi)$, and perturbation retention, $\Sec=\rmI(c_\pi;\tilde c_\pi)$. Here $\Sec$ is a retention-channel quantity, not a direct measure of exploit success or vulnerable-code generation....