Related papers: Why Neural Structural Obfuscation Can't Kill White…

Contributions to AI: This paper proposes a neuro-symbolic search architecture integrating discrete rule-based logic with lightweight Neural Network Feedback Control (NNFC). Utilizing cascade filtering to isolate neural mispredictions while…

Convolutional Neural Networks (CNNs) have emerged as highly successful tools for image generation, recovery, and restoration. A major contributing factor to this success is that convolutional networks impose strong prior assumptions about…

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

Tomography inference attacks aim to reconstruct network topology by analyzing end-to-end probe delays. Existing defenses mitigate these attacks by manipulating probe delays to mislead inference, but rely on two strong assumptions: (i) probe…

We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of autonomous and other complex systems without unduly…

Deep Symbolic Optimization (DSO) is a novel computational framework that enables symbolic optimization for scientific discovery, particularly in applications involving the search for intricate symbolic structures. One notable example is…

The intellectual property of deep generative networks (GNets) can be protected using a cascaded hiding network (HNet) which embeds watermarks (or marks) into GNet outputs, known as box-free watermarking. Although both GNet and HNet are…

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Screen-shooting robust watermarking aims to imperceptibly embed extractable information into host images such that the watermark survives the complex distortion pipeline of screen display and camera recapture. However, achieving high…

Deep neural networks (DNNs) have achieved remarkable success in computer vision but remain highly vulnerable to adversarial attacks. Among them, camouflage attacks manipulate an object's visible appearance to deceive detectors while…

Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cognitive Overload (SCO), a byproduct of the contention between…

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…

Generalization of machine learning models can be severely compromised by data poisoning, where adversarial changes are applied to the training data. This vulnerability has led to interest in certifying (i.e., proving) that such changes up…

Network Intrusion Detection Systems (NIDS) have been studied for decades. Hundreds of papers have, e.g., proposed ways to enhance, harden or bypass NIDS. However, the findings of prior literature are hardly reflected in real-world…

Convolutional Neural Networks (CNNs) have recently become a favored technique for image denoising due to its adaptive learning ability, especially with a deep configuration. However, their efficacy is inherently limited owing to their…

Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and…

Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept…

Erasure codes offer an efficient way to decrease storage and communication costs while implementing atomic memory service in asynchronous distributed storage systems. In this paper, we provide erasure-code-based algorithms having the…

Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's…

Automatic neural architecture design has shown its potential in discovering powerful neural network architectures. Existing methods, no matter based on reinforcement learning or evolutionary algorithms (EA), conduct architecture search in a…