New neural network method hides input information in complex-valued features to protect privacy.
problem Preventing adversaries from inferring input attributes from neural network features.
method Transforming real-valued features into complex-valued ones, making input hidden in a randomized phase.
result Significantly diminishes adversary's ability to infer input while preserving high accuracy.
Survey on spectral gaps of random hyperbolic surfaces.
problem Understanding spectral gaps of random hyperbolic surfaces.
method Brief survey on geometry and spectra, discussion of results by Hide-Magee, Anantharaman-Monk, and Hide-Macera-Thomas.
result Near optimal spectral gaps for random surfaces.
Proposes QNN to protect input privacy in neural networks.
problem Protecting input privacy in neural networks.
method Quaternion-valued neural network (QNN) to hide input information.
result QNN effectively protects input privacy without significant accuracy loss.
A game theory study on optimal hiding and searching strategies in discrete locations.
problem Optimal hiding and searching strategies in a two-person zero-sum game between a hider and a searcher.
method Proved the existence of optimal strategies, developed an algorithm to compute them, and compared with a simple strategy.
result Optimal hiding strategy involves hiding in each location with nonzero probability, and optimal searching strategy can be constructed with up to n simple sequences.
Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.
problem Lack of formal proofs of privacy in PP-GANs for image sanitization.
method Subverted PP-GANs for facial expression recognition to hide sensitive data in sanitized images.
result It is possible to hide sensitive identification data in sanitized PP-GAN output images, even allowing reconstruction of entire input images.
Hides the complexity of neural networks, making them more transparent.
problem Lack of transparency in Neural Networks hinders their adoption.
method Proposes Hide-and-Seek (HnS) framework for training interpretable neural networks.
result Interpretable neural networks can be trained without sacrificing predictive power.
SteganoGAN hides data in images with high capacity and high quality.
problem Hiding secret messages in images without detection.
method Generative adversarial networks (GANs) to optimize image quality and payload size.
result Achieves 4.4 bits per pixel payload, evades steganalysis, works on multiple datasets.
AutoDIME automates design of multi-agent environments for RL.
problem Designing multi-agent environments for reinforcement learning is challenging.
method Developed intrinsic teacher rewards for multi-agent settings and evaluated them in various tasks.
result Value disagreement was found to be most consistent and effective across tasks.
Matryoshka hides secret models in a carrier model, achieving high capacity and robustness.
problem Stealing functionality of private ML data by hiding models in a carrier model.
method Parameter sharing approach exploiting the learning capacity of the carrier model.
result Hides a 26x larger secret model or 8 secret models in the carrier model.
Agents learn sophisticated tool use and coordination in hide-and-seek.
problem Training agents to perform complex tasks in multi-agent environments.
method Multi-agent competition with hide-and-seek as a simple objective.
result Agents develop emergent strategies requiring sophisticated tool use and coordination.
Adversarial attacks hide cyber-physical attacks in ICS.
problem Hiding cyber-physical attacks in industrial control systems.
method Modeling an attacker compromising sensors, manipulating data, and evaluating attacks on both continuous and mixed data.
result Successfully hides cyber-physical attacks with 2.87 out of 12 sensors compromised on average.
Paper shows how to hide individuals in graphs to fool community detection models.
problem Adversarial attack on community detection models by hiding individuals.
method Iterative learning framework that updates a graph generator and a community detection model.
result Adversarial graphs generated by the method can fool multiple community detection models.
Noise injection improves inference privacy in DNN models.
problem Malicious servers can infer sensitive attributes from input data.
method Adaptive Noise Injection (ANI) using a lightweight DNN on the client.
result Significant improvement in privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy).
The paper shows examples of 2-complexes that can't be embedded in R^4, hiding obstructions in higher Milnor invariants.
problem Embedding 2-complexes in R^4 with hidden obstructions.
method Provides examples of 2-complexes and families of PL immersions that hide embedding obstructions.
result Embedding obstructions vanish for the given examples, answering a question in Avramidi-Okun-Schreve's paper.
Secret neural networks hidden within trained models.
problem Excess capacity in neural networks allows embedding secret models.
method Novel framework for hiding secret neural networks within carrier networks.
result Detection of hidden networks is computationally infeasible.
Deep neural networks improve speech steganography for covert messaging.
problem Improving steganography for speech data using deep learning.
method Proposed a new deep neural network model with short-time Fourier transform layers, demonstrating effectiveness on multiple speech datasets.
result Demonstrated that the proposed method can conceal multiple messages in a single carrier and is robust to channel distortions.
As machine learning systems move from computer-science laboratories into the open world, their accountability becomes a high priority problem. Accountability requires deep understanding of system behavior and its failures. Current evaluation methods such as single-score error metrics and confusion matrices provide aggr…
Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework called PR-GAN that offers privacy-preserving mechanism using generative adversarial …
Challenge hides and seeks privacy in clinical time-series data.
problem De-identifying clinical time-series data while preserving utility and privacy.
method Synthetic data generation to preserve temporal dynamics and limit re-identification risk.
result A novel competition tracks synthetic data generation and patient re-identification.
Paper proposes a method to detect glare in document images.
problem Glare obscures text in document images, hindering recognition.
method Divides document into blocks, collects luminance and histogram features, uses CNN to detect glare.
result High recall and f-score in detecting glare.
Develops Shapley explainability solutions respecting data manifold.
problem Tenable assumption of uncorrelated features in Shapley explainability.
method Two solutions: generative modelling and direct learning of Shapley value-function.
result On-manifold Shapley explainability overcomes drawbacks of 'off-manifold' values.
Paper shows LIME and SHAP explanations can be fooled by adversarial attacks.
problem Reliability of post hoc explanation methods like LIME and SHAP.
method Adversarial attack technique to hide classifier biases.
result Popular explanation techniques can be fooled into generating biased explanations.
Shapley Flow interprets model predictions using a graph-based approach to feature importance.
problem Existing feature importance methods ignore or hide feature dependencies.
method Shapley Flow considers the entire causal graph and assigns credit to edges.
result Shapley Flow provides a deeper, graph-based view of feature importance.
New technique hides adversarial attacks in complex images, making them imperceptible.
problem Lack of interpretability in Convolutional Neural Networks (CNNs) and vulnerability to adversarial attacks.
method Developed a technique that hides adversarial attacks in regions of high complexity, making them imperceptible to human observers.
result Significant evidence of concealment of adversarial attacks in images, making them imperceptible to human observers.
Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric informat…
The study measures feature importance in models by randomly ablating features and averaging loss changes.
problem Measuring feature importance in machine learning models.
method Randomly ablating features and averaging loss changes over many points and replacements.
result Uncertainty measures of feature importance are presented.
HiDe learns hierarchical control for complex tasks by separating planning and control.
problem Solving long horizon control tasks with generalization to unseen scenarios.
method Functional decomposition of state-action spaces, RL-based planner, modular transfer of policy layers.
result Generalizes across unseen test environments and scales to longer horizons.
New algorithm reduces matrix multiplication time for sparse matrices.
problem Efficiently multiply large sparse matrices with limited space.
method Exploits sparsity to reduce QR decompositions and time complexity.
result Time complexity reduced to $\widetilde{O}\left((
nz(X)+
nz(Y))\ell+n\ell^2
ight)$ in expectation.
We study the performance of a family of randomized parallel coordinate descent methods for minimizing the sum of a nonsmooth and separable convex functions. The problem class includes as a special case L1-regularized L1 regression and the minimization of the exponential loss ("AdaBoost problem"). We assume the input da…
Measures faithfulness of LLM explanations to reveal hidden biases and misleading claims.
problem LLM explanations can misrepresent the model's reasoning process, leading to over-trust and misuse.
method Defines faithfulness in terms of concept influence and uses counterfactuals and Bayesian models to estimate it.
result Can quantify and discover interpretable patterns of unfaithfulness in LLM explanations.
Teaches sequential learners with changing inner states to improve future performance.
problem Teaching sequential learners with evolving inner states.
method Introduces an optimal control approach for multi-agent learning.
result Optimal control approach improves future performance of learners.
Develops framework to analyze pruning of neural networks.
problem Understanding pruning of neural networks in non-imaging data.
method Develops framework to plant and hide winning tickets in neural networks.
result Similar trends in ticket sparsity observed across different tasks.
A stealthy framework injects faults into DNNs to misclassify images without affecting overall accuracy.
problem Vulnerability of deep neural networks to misclassification attacks.
method Fault sneaking attack using ADMM optimization with constraints on maintaining model accuracy and minimizing parameter modifications.
result The framework can inject multiple sneaking faults into DNNs without reducing overall accuracy.
The paper explores maximal perturbations to hide certain attributes in data while keeping the model's performance intact.
problem Protecting sensitive attributes from both model and human detection.
method Adversarial perturbations applied to raw data to conditionally damage model's classification of one attribute while preserving the rest.
result Maximal perturbations can hide certain attributes from both model and human detection, impacting model performance but not human perception.
A novel approach to federated learning with strong privacy guarantees.
problem Maintaining privacy of clients' data and federator's objective in federated learning.
method Inspired by knowledge distillation and private information retrieval, the approach combines secret-sharing-based multi-party computation and graph-based private information retrieval.
result Strong information-theoretic privacy guarantees for federated learning.
Adversarial machine learning hides 5G communications from eavesdroppers.
problem Hiding 5G communications from eavesdroppers using DL classifiers.
method Craft adversarial perturbations to fool DL classifiers.
result Adversarial perturbations can hide 5G communications with high probability.
Exact cluster recovery with same-cluster queries for arbitrary ellipsoidal clusters.
problem Recovering clusters from same-cluster queries in arbitrary ellipsoidal clusters.
method Relaxing spherical k-means assumption to arbitrary ellipsoidal clusters, designing an algorithm with logarithmic query complexity. result Exact recovery of clusters using O(k3lnklnn) queries and ildeO(kn+k3) time. We propose a privacy-enhanced matrix factorization recommender that exploits the fact that users can often be grouped together by interest. This allows a form of "hiding in the crowd" privacy. We introduce a novel matrix factorization approach suited to making recommendations in a shared group (or nym) setting and the …
Defense against small image patches using occlusions.
problem Vulnerability of deep learning to small adversarial patches.
method Partially occlude image around each patch location.
result Certified security against patch attacks of a certain size.
Proposes fair classification method using Wasserstein-1 distances.
problem Ensuring fairness in classification models by protecting sensitive information.
method Minimizes Wasserstein-1 distances to enforce independence between classifier outputs and sensitive information.
result Empirical performance superior to fairness baselines on benchmark datasets.
The Pinned AUC metric hides unintended bias when class distributions vary.
problem Unintended bias in classification models.
method Examines the Pinned AUC metric and its limitations.
result Pinned AUC can obscure different types of unintended bias.
Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most existing detection mechanisms against adversarial attacksimpose significant costs, either by using additional classifiers to spot adversaria…
NeuroMask provides interpretable explanations for deep neural networks.
problem Understanding how deep neural networks make decisions.
method Applies a mask to reveal or hide parts of an image, tuning mask values to preserve classification results and produce interpretable explanations.
result NeuroMask successfully localizes the most relevant parts of an image to a deep neural network's decision.
TIPRDC anonymizes data features to protect privacy while retaining useful information.
problem Privacy concerns from crowdsourced data hinder deep learning applications.
method Hybrid training method combining adversarial and mutual information estimation.
result Feature extractor hides private information while preserving original data features.
Improved shuffling technique amplifies privacy guarantees for anonymous data contributions.
problem Enhancing privacy in systems where data is contributed anonymously.
method Developed a new approach to random shuffling that amplifies differential privacy guarantees.
result Achieved asymptotically optimal privacy amplification with nearly optimal dependence in ε.
Proposes fair mapping to prevent bias in model predictions without distorting data.
problem Reduces bias in model predictions without altering the data distribution.
method Uses Wasserstein GAN and AttGAN frameworks to transform data distributions while preserving privacy and interpretability.
result Preserves data interpretability and fairness in subsequent analysis tasks.
CycleGAN (Zhu et al. 2017) is one recent successful approach to learn a transformation between two image distributions. In a series of experiments, we demonstrate an intriguing property of the model: CycleGAN learns to "hide" information about a source image into the images it generates in a nearly imperceptible, high-…
Missing data imputation can help improve the performance of prediction models in situations where missing data hide useful information. This paper compares methods for imputing missing categorical data for supervised classification tasks. We experiment on two machine learning benchmark datasets with missing categorical…