Search Results for author:
Found 18 papers, 5 papers with code
Removing Undesirable Concepts in Text-to-Image Generative Models with Learnable Prompts
Generative models have demonstrated remarkable potential in generating visually impressive content from textual descriptions.
BAIT: Benchmarking (Embedding) Architectures for Interactive Theorem-Proving
We also provide a qualitative analysis, illustrating that improved performance is associated with more semantically-aware embeddings.
Adversarial Robustness on Image Classification with $k$-means
In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations.
It's Simplex! Disaggregating Measures to Improve Certified Robustness
Certified robustness circumvents the fragility of defences against adversarial attacks, by endowing model predictions with guarantees of class invariance for attacks up to a calculated size.
Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus.
Generating Adversarial Examples with Task Oriented Multi-Objective Optimization
The key factor for the success of adversarial training is the capability to generate qualified and divergent adversarial examples which satisfy some objectives/goals (e. g., finding adversarial examples that maximize the model losses for simultaneously attacking multiple models).
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness.
Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity
In response to subtle adversarial examples flipping classifications of neural network models, recent research has promoted certified robustness as a solution.
Transferable Graph Backdoor Attack
In this paper, we disclose the TRAP attack, a Transferable GRAPh backdoor attack.
Improving Robustness with Optimal Transport based Adversarial Generalization
More specifically, by minimizing the WS distance of interest, an adversarial example is pushed toward the cluster of benign examples sharing the same label on the latent space, which helps to strengthen the generalization ability of the classifier on the adversarial examples.
Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learning
Central to this approach is the selection of positive (similar) and negative (dissimilar) sets to provide the model the opportunity to `contrast' between data and class representation in the latent space.
Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier.
Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness
An important technique of this approach is to control the transferability of adversarial examples among ensemble members.
Improving Adversarial Robustness by Enforcing Local and Global Compactness
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application.
Perturbations are not Enough: Generating Adversarial Examples with Spatial Distortions
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier.
Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection
Due to the sharp increase in the severity of the threat imposed by software vulnerabilities, the detection of vulnerabilities in binary code has become an important concern in the software industry, such as the embedded systems industry, and in the field of computer security.
Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting.
Reinforcement Learning for Autonomous Defence in Software-Defined Networking
Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification.
