A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of disparate vulnerability against MIAs: unequal success rate of MIAs against diff…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Model Vulnerability”
Each year, thousands of software vulnerabilities are discovered and reported to the public. Unpatched known vulnerabilities are a significant security risk. It is imperative that software vendors quickly provide patches once vulnerabilities are known and users quickly install those patches as soon as they are available…
Study reveals how high-dimensional models are vulnerable to consistent adversarial attacks.
problem Understanding the vulnerability of high-dimensional linear classifiers to adversarial attacks.
method Introducing a new error metric to quantify model vulnerability, and rigorously characterizing these metrics in asymptotic settings.
result As models become more overparameterized, their vulnerability to label-preserving perturbations increases.
Study on measuring vulnerability of neural network parameters via corruption.
problem Understanding the robustness and generalization of deep neural networks.
method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.
result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.
We are concerned with the vulnerability of computer vision models to distributional shifts. We formulate a combinatorial optimization problem that allows evaluating the regions in the image space where a given model is more vulnerable, in terms of image transformations applied to the input, and face it with standard se…
Thousands of security vulnerabilities are discovered in production software each year, either reported publicly to the Common Vulnerabilities and Exposures database or discovered internally in proprietary code. Vulnerabilities often manifest themselves in subtle ways that are not obvious to code reviewers or the develo…
New method certifies joint adversarial robustness of model ensembles.
problem Ensuring robustness of model ensembles against adversarial attacks.
method Proposes a novel technique to certify joint robustness, building on prior work on single-model robustness certification.
result Demonstrates the effectiveness of certifying joint robustness of ensembles, improving understanding of ensemble defenses.
The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by the many vulnerabilities reported on a daily basis. This calls for machine learning methods for vulnerability detection. Deep learning is attractive for this purpose because it a…
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
problem Diverse adversarial vulnerabilities for robust ensemble models.
method Isolates and diversifies adversarial vulnerabilities through distillation and training.
result Achieves higher robustness against transfer attacks compared to previous methods.
The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?cs.CL
Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.
problem Language model benchmarks fail to accurately reflect true language understanding and adaptability.
method Systematic analysis of NLP evaluation frameworks, identifying vulnerabilities in static benchmarks, human evaluation protocols, and LLM-as-judge frameworks.
result Current evaluation methods are unreliable and need improvement to accurately assess LLM performance.
Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical applications. In this paper, we conjecture that the leading cause of adversarial vulnerabili…
Study identifies key parameters and input dimensions making LLMs and VLMs brittle.
problem Vulnerability of large language and vision-language models to perturbations.
method Proposed FI measure based on information geometry to quantify sensitivity.
result Small subset of high FI parameters significantly contribute to brittleness.
An alternative proof of the vulnerability of retrieval in high intrinsic dimensionality neighborhoodcs.LG
The paper analyzes how much data points can be altered to change their rank in nearest neighbor searches.
problem Vulnerability of nearest neighbor search in high-dimensional data.
method Statistical analysis of perturbation needed to change neighbor rank.
result Derived statistical distribution of perturbation needed to modify neighbor rank.
Pricing vulnerable options in a hybrid credit risk model driven by Heston-Nandi GARCH processesq-fin.PR
This paper proposes a hybrid credit risk model, in closed form, to price vulnerable options with stochastic volatility. The distinctive features of the model are threefold. First, both the underlying and the option issuer's assets follow the Heston-Nandi GARCH model with their conditional variance being readily estimat…
Paper tackles model vulnerabilities by reconstructing training data.
problem Reconstructing training data from model parameters poses a security risk.
method Developed a mathematical framework and score matching method for both Bayesian and non-Bayesian models.
result First score matching framework for reconstructing data in Bayesian models.
Boosting algorithms predict financial vulnerability of farmers in Chile and Tunisia.
problem Predict financial vulnerability of farmers in Chile and Tunisia using environmental data.
method Interpretable boosting algorithms based on ridge-regularized generalized linear models.
result Interaction effects improve predictive power only when included in two-step boosting.
Increasing numbers of software vulnerabilities are discovered every year whether they are reported publicly or discovered internally in proprietary code. These vulnerabilities can pose serious risk of exploit and result in system compromise, information leaks, or denial of service. We leveraged the wealth of C and C++ …
Study bounds for prices of European and American options with optional termination.
problem Bounding prices of options with potential termination.
method Duality results linking upper prices of vulnerable options to American options with constrained exercise times.
result Linking upper prices of vulnerable options to American options and game options.
Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs. Surprisi…
Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult. In this work we show that the reverse problem---making models more vulnerable---is surprisingly easy. After presenting some proofs of concept on MNIST, we introduce a generic tilting attack that injects …
Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inferencestat.ML
Overparameterized models are more vulnerable to membership inference attacks.
problem Vulnerability of overparameterized models to membership inference attacks.
method Theoretical and empirical analysis of overparameterized linear and ridge-regularized linear regression models in the Gaussian data setting.
result Increased number of parameters and model complexity increase vulnerability to membership inference attacks.
On Vulnerability Conditional Risk Measures: Comparisons and Applications in Cryptocurrency Marketq-fin.RM
New risk measures assess cryptocurrency market vulnerabilities during financial distress.
problem Capturing systemic risk in cryptocurrency markets during financial distress.
method Introducing Vulnerability Conditional Risk Measures (VCoES) and related measures.
result Validated theoretical insights and demonstrated practical relevance in cryptocurrency market.
This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.
problem The effectiveness of targeted data poisoning attacks is often overestimated due to average evaluation methods.
method The paper introduces metrics to identify the hardest and easiest to poison samples based on clean model information.
result The proposed metrics reliably stratify samples by poisoning vulnerability, enabling rigorous worst-case evaluation and proactive defense.
Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the networks. In this paper, using information geometry, we provide a reasonable explanation for the vulnerability of deep learning models. By consi…
New method defends RL agents from poisoning attacks without MDP knowledge.
problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.
Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or when the adversary controls the training algorithm. However, when the model is no…
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the…
This study examines how model architecture affects deep learning model privacy.
problem Privacy concerns in deep learning models due to potential leakage of sensitive information.
method Investigation of CNNs and Transformers, focusing on activation layers, stem layers, LN layers, and attention modules.
result Transformers generally exhibit higher vulnerability to privacy attacks than CNNs.
Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities …
Preschool attendance correlates with lower developmental vulnerabilities in Queensland, Australia.
problem Understanding the relationship between preschool attendance and developmental vulnerabilities in different regions.
method Data Analysis and Machine Learning to identify clusters of socio-demographic variables.
result Identified three clusters with varying socio-demographic variables affecting the relationship between preschool attendance and developmental vulnerabilities.
Paper shows large models are vulnerable to poisoning attacks.
problem Vulnerability of large machine learning models to poisoning attacks.
method Analyzed isotropic random feature vectors and geometric median as robust gradient aggregator rule.
result Linear and logistic regressions with parameters are vulnerable to arbitrary manipulation by poisoners.
VERA-V uses variational inference to discover vulnerabilities in multimodal vision-language models.
problem Existing methods for jailbreaking vision-language models are brittle, limited, and focus on single attacks.
method VERA-V recasts jailbreak discovery as learning a joint posterior distribution over text-image prompts, using variational inference and three complementary strategies.
result VERA-V consistently outperforms state-of-the-art baselines, achieving up to 53.75% higher attack success rate.
The impact of margin trading on share price evolution: A cascading failure model investigationq-fin.GN
Margin trading in which investors purchase shares with money borrowed from brokers is blamed to be a major cause of the 2015 Chinese stock market crash. We propose a cascading failure model and examine how an increase in margin trading increases share price vulnerability. The model is based on a bipartite graph of inve…
This work examines how adversarial vulnerability changes with the dimensionality of the subspace of perturbations.
problem Understanding adversarial vulnerability in constrained input spaces.
method Investigates adversarial vulnerability in subspace of the input space with varying dimensions, using PGD attacks and analyzing the dependence on and .
result Adversarial success of PGD attacks is a monotonically increasing function of $ε( rac{dim(V)}{dim(X)})^{ rac{1}{q}}$.
Vulnerability identification is crucial to protect the software systems from attacks for cyber security. It is especially important to localize the vulnerable functions among the source code to facilitate the fix. However, it is a challenging and tedious process, and also requires specialized security expertise. Inspir…
BadGD identifies gradient descent vulnerabilities through strategic backdoor attacks.
problem Gradient descent vulnerabilities through malicious data manipulation.
method Introduces Max RiskWarp, Max GradWarp, and Max GradDistWarp triggers to exploit gradient descent.
result Demonstrates how malicious triggers can significantly alter loss landscapes and gradient calculations.
This paper analyzes how data and model properties affect membership inference attacks.
problem Understanding and mitigating the vulnerability of machine learning models to membership inference attacks.
method Empirical analysis of data and model properties on MIA success.
result Data and model properties, not just model overfitting, influence MIA success.
Using a suitable change of probability measure, we obtain a novel Poisson series representation for the arbitrage- free price process of vulnerable contingent claims in a regime-switching market driven by an underlying continuous- time Markov process. As a result of this representation, along with a short-time asymptot…
Generative text classifiers are most vulnerable to membership inference attacks.
problem Privacy threat from Membership Inference Attacks on generative text classifiers.
method Comprehensive empirical evaluation of generative, discriminative, and pseudo-generative classifiers across various datasets.
result Generative classifiers explicitly modeling are most vulnerable to membership leakage.
Deep networks can overfit benignly but still be vulnerable to adversarial attacks.
problem Adversarial vulnerability of deep neural networks trained with benign overfitting.
method Investigated causes of adversarial vulnerability, identified label noise as a key factor, and explored the impact of training procedures and representation learning.
result Adversarial robustness requires more complex decision boundaries than simple ones, suggesting the need for better representation learning.
Graph Backdoorcs.LG
GTA is the first backdoor attack on GNNs, demonstrating vulnerabilities in graph-oriented security models.
problem Vulnerability of graph neural networks to backdoor attacks.
method Graph-oriented triggers, dynamic adaptation, model-agnostic, attack-extensible.
result Demonstrates severe threats to graph classification and node classification tasks.
New normalization method makes neural networks more robust to adversarial attacks.
problem Adversarial vulnerability of BatchNorm in deep neural networks.
method Identified distribution shift caused by adversarial images, proposed RobustNorm to use inference-time statistics.
result RobustNorm makes models more robust to adversarial attacks without sacrificing BatchNorm benefits.
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to use the methodology of adversarial training. We analyze the adversarially train…
DL models for MTS regression are vulnerable to adversarial attacks, posing risks in safety-critical applications.
problem Vulnerability of DL models to adversarial examples in MTS regression.
method Adversarial attack generation techniques from image classification were adapted for MTS.
result All state-of-the-art DL regression models (CNN, LSTM, GRU) are vulnerable to adversarial attacks.
Paper proposes a new ML approach to estimate g-vulnerability without estimating conditional probabilities.
problem Estimating information leakage in black-box systems with large output domains.
method Developed a novel ML-based approach to estimate g-vulnerability without estimating conditional probabilities.
result The proposed method outperforms frequentist approach when dealing with large output domains.
Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial l…
New method uses model's generalization gap to predict membership inference attacks.
problem Predicting membership inference attacks on machine learning models.
method Uses the model's generalization gap as a metric to estimate the vulnerability to membership inference attacks.
result Demonstrates that the model's generalization gap provides an upper bound on MIA security.
The paper tackles adversarial robustness by maximizing worst-case mutual information.
problem Training robust machine learning models against adversarial inputs is challenging.
method Develops a notion of representation vulnerability and an unsupervised learning method to maximize worst-case mutual information.
result Proves a lower bound on minimum adversarial risk and supports robustness of representations.