GRAM improves generative models without saddlepoint optimization.
problem Training deep generative models with saddlepoint optimization is challenging.
method GRAM uses a fixed kernel as an adversary instead of a critic network.
result GRAM networks match and outperform adversarial training in generative quality.
New algorithm for minimizing regret in adversarial dueling bandits.
problem Minimizing regret in dueling bandits with adversarial feedback.
method Introduced an algorithm with T T T -round regret of i l d e O ( K 1 / 3 T 2 / 3 ) ilde{O}(K^{1/3}T^{2/3}) i l d e O ( K 1/3 T 2/3 ) . result Algorithm achieves Ω ( K 1 / 3 T 2 / 3 ) Ω(K^{1/3}T^{2/3}) Ω ( K 1/3 T 2/3 ) regret lower bound. WaveFit uses fixed-point iteration to create high-quality neural vocoders.
problem Creating high-quality neural vocoders with fast inference.
method Integrates GANs' adversarial training into a DDPM-like iterative framework based on fixed-point iteration.
result WaveFit synthesizes speech with naturalness comparable to human speech, and is significantly faster than existing methods.
New model for display advertising with stochastic and adversarial components.
problem Display advertising with stochastic and adversarial click-through-rates.
method Adversarial scaling model; two algorithms tested: action elimination and mirror descent.
result Two algorithms are robust to adversarial scaling.
Study on how adversarial training affects neural network kernels and robustness.
problem Understanding and improving adversarial robustness in neural networks.
method Empirical study of the evolution of the empirical Neural Tangent Kernel (NTK) under standard and adversarial training.
result Adversarial training leads to a new kernel that provides robustness, even when non-robust training is performed on top of it.
New approaches improve adversarial robustness of DEQs.
problem Adversarial vulnerability of DEQs.
method Developed approaches to estimate intermediate gradients and integrate them into attacking pipelines.
result Demonstrated adversarial robustness of DEQs competitive with deep networks.
The paper tackles targeted attacks on rank aggregation methods, proving the fixed point of adversarial game.
problem The security issue of rank aggregation methods, especially the vulnerability to targeted attacks.
method Formulated as a game-theoretic framework, the attack behavior is a fixed point of the composition of the adversary and the victim.
result The victims will produce the target ranking list once the adversary has complete information.
MARGINATTACK improves zero-confidence adversarial attacks' accuracy and efficiency.
problem Improving zero-confidence adversarial attacks' accuracy and efficiency.
method Proposes MARGINATTACK, a zero-confidence attack framework that computes margin with improved accuracy and efficiency.
result MARGINATTACK computes a smaller margin than state-of-the-art zero-confidence attacks and matches state-of-the-art fix-perturbation attacks.
Framework learns encodings to protect private attributes from inference.
problem Protect private attributes from inference in image encodings.
method Adversarial training of deep neural networks to inhibit classifier learning.
result Stable optimization approach yields encoders resistant to privacy inference.
Adversarial attacks found to be effective on code models.
problem Adversarial robustness of code models.
method Instantiated adversarial attacks for code, demonstrated vulnerability, and improved robustness.
result Neural models for code are vulnerable to adversarial attacks.
Study shows multi-source learning is more resilient to adversarial corruption than single-source learning.
problem Learning from multiple untrusted data sources, especially when some are adversarially corrupted.
method Analyzed the scenario where an adversary can corrupt a fixed fraction of data sources, derived a generalization bound for this setting.
result PAC-learnability is possible in the multi-source setting even when some data sources are adversarially corrupted.
New method enhances neural network robustness against adversarial attacks.
problem Enhancing neural network robustness against adversarial attacks.
method Variational framework with per-sample noise level selector.
result Enhanced empirical robustness and certified robustness.
Study on adversarial training dynamics in high dimensions using SGD.
problem Analyzing adversarial training of models in high-dimensional settings.
method Deriving deterministic equivalents for SGD iterates under Gaussian mixtures.
result No constant learning rate guarantees monotone descent in adversarial training.
Maximizes influence in adversarial networks by choosing optimal seed nodes.
problem Maximizing influence in networks with an adversarial edge specification.
method Formulated as a repeated game between player and adversary, with online node selection.
result Established upper and lower bounds on minimax pseudo-regret.
New definition shows no trade-off between adversarial and standard accuracy.
problem Inexact definition of adversarial perturbation causes confusion.
method Proposed a slight modification to adversarial perturbation definition.
result Existence of classifiers that are robust and achieve high standard accuracy.
Unified formulation bridges adversarial and nonstationary bandits.
problem Handling time-varying reward distributions in multi-armed bandit problems.
method Unified oracle that switches between adversarial and nonstationary bandit oracles based on window size.
result Optimal regret achieved with matching lower bound.
Automated discovery of adaptive attacks improves adversarial defense evaluation.
problem Challenges in reliably evaluating adversarial defenses.
method Formalizes adaptive attacks as reusable building blocks in a search space for automatic discovery.
result Our tool discovers significantly stronger attacks than AutoAttack, improving adversarial defense evaluation.
Adaptive algorithm generates unrestricted adversarial inputs, defeating robust classifiers.
problem Vulnerability of neural networks to unrestricted adversarial inputs.
method Adaptive algorithm for generating unrestricted adversarial inputs.
result Adversarial inputs defeat robust classifiers.
Heuristics for solving privacy setting problems in neural networks.
problem Maximin problem in generative adversarial privacy setting.
method Greedy algorithm for linear adversaries and alternately optimizing for CNN adversaries.
result The greedy algorithm performs better as the number of instances increases.
Adversarial training adds dynamic perturbations to neural networks for robustness.
problem Accuracy trade-off and lack of diversity in adversarial examples.
method Dynamic adversarial perturbations in the parameter space of neural networks, updating perturbation biases during training.
result Adversarial training with negligible cost and reduced accuracy trade-off.
We improve adversarial robustness calibration analysis for broader hypothesis sets.
problem Improving calibration for adversarial robustness in machine learning.
method A finer definition of calibration for adversarial robustness.
result Our results cover most common hypothesis sets in machine learning.
Empirical study on SGD hyperparameters and adversarial robustness.
problem Effect of SGD hyperparameters on adversarial robustness and generalization.
method Empirical observation of learning rate, batch size, and momentum effects on adversarial robustness and generalization.
result Constant learning rate to batch size ratio leads to good generalization and almost constant adversarial robustness.
Improved algorithm for bandits with delayed feedback, combining adversarial and stochastic performance.
problem Adversarial and stochastic multiarmed bandits with delayed feedback.
method Modified Zimmert and Seldin's algorithm with near-optimal regret guarantees.
result Near-optimal regret guarantees in both adversarial and stochastic settings.
MMA training maximizes margins for adversarial robustness.
problem Adversarial robustness of neural networks.
method Directly maximizes margins through adaptive adversarial training.
result MMA training improves adversarial robustness compared to fixed ε adversarial training.
Robust RL with learned optimal adversary improves agent performance under adversarial state observations.
problem Ensuring reinforcement learning agents' robustness against adversarial perturbations of state observations.
method Proposed a framework of alternating training with learned adversaries (ATLA) to find optimal adversarial policies and enhance agent robustness.
result ATLA achieves state-of-the-art performance under strong adversaries in continuous control environments.
Universal perturbations misclassify text with high accuracy.
problem Vulnerability of text classifiers to small perturbations.
method Algorithm to compute universal adversarial perturbations.
result Deep neural networks are highly vulnerable to universal adversarial perturbations.
Our work investigates how to identify privacy violations in models using finite adversaries.
problem Identifying privacy violations in models with limited adversary capabilities.
method Investigates requirements for finite adversaries to identify privacy violations.
result Parameters quantify the capabilities of finite adversaries.
A new efficient PGD method generates smaller perturbation adversarial examples.
problem Adversarial examples in deep neural networks.
method Modified Project Gradient Descent (PGD) method for ensemble models.
result Generates smaller perturbation adversarial examples than PGD method.
New method UADs improves transferability of adversarial perturbations.
problem Transferability of adversarial perturbations across different DNN architectures.
method Proposes Universal Adversarial Directions (UADs) to improve transferability.
result UADs can achieve a Nash equilibrium, indicating potential transferability.
Improved online learning algorithms using ADP for adversarial environments.
problem Minimizing regret in adversarial online learning with vector-valued losses.
method Approximate dynamic programming to characterize lower Pareto frontier of expected losses.
result Improved performance bounds compared to existing online learning algorithms.
Defends classifiers from adversarial attacks using self-supervised data estimation.
problem Protecting classifiers from adversarial attacks with full attacker access.
method RIDE, a self-supervised learning algorithm for individual data estimation.
result Significant improvement in adversarial defense performance (98%, 76%, 43% test accuracy on MNIST, CIFAR-10, and ImageNet datasets respectively).
ASA improves ASR by adapting SD models to SI model's deep feature distribution.
problem Improving ASR performance on new speakers with limited data.
method Adversarial learning to regularize SD model's deep features to match SI model's.
result ASA achieves significant word error rate improvements over SI models.
New bandit problem for maintaining revenue above baseline.
problem Maximizing revenue while maintaining a fixed baseline over time.
method Proposes novel strategies for stochastic and adversarial settings, analyzes regret bounds.
result Proves high probability and expectation bounds on regret, shows almost optimal algorithm for stochastic setting.
RG framework assesses deep learning vulnerability to small changes and attacks.
problem Assessing deep learning networks' sensitivity to input data changes and adversarial attacks.
method Renormalisation Group (RG) framework with Monte Carlo ideas to identify relevant operators and sensitivity directions.
result Trained deep-learning networks can be tested for robustness and dangerous perturbations identified.
Two quantization-based defenses improve CNN robustness against adversarial attacks.
problem Adversarial examples threaten machine learning, especially CNNs.
method Constant Quantization (CQ) and Trainable Quantization (TQ) to increase CNN robustness.
result Significant increase in classification accuracy of perturbed images.
New algorithms achieve no-regret learning even with adversarial transitions and losses.
problem No-regret learning impossible with adversarial transitions and losses.
method Developed algorithms for adversarial Markov Decision Processes with smooth regret increase.
result Achieved O ~ ( T + C e x t s f P ) \widetilde{O}(\sqrt{T} + C^{ extsf{P}}) O ( T + C e x t s f P ) regret, with C e x t s f P C^{ extsf{P}} C e x t s f P measuring adversarial transition function. New metrics fail adversarial tests, with some more robust than others.
problem Evaluation metrics for time-series anomaly detection were improved but not fully robust.
method Adversarial stress-testing of 12 adopted metrics on real benchmarks.
result Some metrics are more robust than others, with ROC-based metrics being gamed more often.
BPN defends against adversarial attacks by generating beneficial perturbations.
problem Adversarial attacks cause deep neural networks to misclassify clean inputs.
method BPN generates beneficial perturbations during training to neutralize future adversarial attacks.
result BPN is robust to adversarial examples and more efficient than classical adversarial training.
This paper explores tradeoffs between standard and adversarial risks in distributionally adversarial training.
problem Understanding the impact of adversarial training on standard risk and adversarial risk.
method Study of distributionally adversarial training with different learning settings and models.
result Derives Pareto-optimal tradeoff curves between standard and adversarial risks.
New adversarial training method improves robustness of power system controllers.
problem Designing robust controllers for complex cyber-physical power systems.
method Adversarial training approach with fixed opponent policy.
result Adversarial trained controllers show useful preventive behaviors in the N-1 problem.
Generative Adversarial Regression (GAR) learns risk scenarios robustly across policies.
problem Learning risk scenarios for conditional risk objectives.
method Generative adversarial framework for risk matching.
result GAR produces more stable and risk-preserving scenarios than baselines.
SARD improves adversarial robustness in two-stage L2D systems.
problem Adversarial attacks can manipulate query allocation in two-stage L2D systems.
method Introduces SARD, a convex learning algorithm with provable guarantees.
result SARD significantly improves robustness under adversarial attacks while maintaining strong clean performance.
This work studies adversarial training in high dimensions, revealing key feature trade-offs.
problem Understanding adversarial robustness in high-dimensional settings.
method Introduces a tractable model to study the geometry of data and adversarial attacks.
result Characterizes directions in data associated with robustness vs. usefulness trade-offs.
WDAIL uses Wasserstein distance for more effective reward shaping in IL.
problem Fixed reward functions in GAIL limit performance on complex tasks.
method Introduces Wasserstein distance and PPO for improved reward shaping and stability.
result Significant performance improvement in complex MuJoCo tasks.
SPLASH units improve deep neural network accuracy and adversarial robustness.
problem Improving deep neural network accuracy and adversarial robustness.
method SPLASH units are learnable activation functions with specific properties that enhance both accuracy and robustness.
result SPLASH units significantly increase adversarial robustness of deep neural networks.
Study on learning strategies in adaptive Markov games with policy regret as metric.
problem Learning in dynamic Markov games with adaptive opponents is challenging.
method Introduced policy regret as a new learning metric and developed algorithms for consistent adaptive adversaries.
result Achieved T \sqrt{T} T policy regret against certain adaptive adversaries. Generative adversarial networks fix aliasing issues by making signals continuous.
problem Alias-free generation in GANs to prevent unwanted information leakage.
method Interpreting all signals as continuous, deriving small architectural changes.
result Generative models match FID of StyleGAN2 but have better internal representations.
Differentiable adversarial attacks improve model robustness in MTPP models.
problem Improving model robustness against adversarial attacks in MTPP models.
method Proposed a differentiable adversarial attack scheme PERMTPP that addresses the sequential nature and varying time-scales of MTPPs.
result Demonstrated offensive and defensive capabilities, and reduced inference times on real-world datasets.