The DoD needs a robust process to evaluate AI/ML model performance and robustness.
problem AI/ML models are brittle and nonrobust, posing risks in national security.
method Reviews AI/ML development process and best practices for evaluation.
result Recommendations for DoD evaluators to ensure robust AI/ML capabilities.
Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by developing methods for explaining the predictions of neural networks. While sev…
As neural networks revolutionize many applications, significant privacy conflicts between model users and providers emerge. The cryptography community developed a variety of techniques for secure computation to address such privacy issues. As generic techniques for secure computation are typically prohibitively ineffec…
Article evaluates AI security threats and proposes multiple measures.
problem Threats to AI integrity and security.
method Literature review, analysis of AI supply chain, discussion of mitigations.
result Multiple protective measures are necessary for AI security.
secml is a Python library for secure and explainable machine learning.
problem Evaluate and understand security and explainability of machine learning models.
method Implement attacks and explainability methods for various algorithms.
result Demonstrates how quickly models fail under adversarial perturbations and visualizes influential features.
New framework assesses LLM security risks in BFSI.
problem Lack of domain-specific security evaluation for LLMs in BFSI.
method Risk-aware evaluation framework combining taxonomy, automated red-teaming, and ensemble judging.
result Higher decoding stochasticity and adaptive interaction lead to more severe disclosures.
Paper revisits PCA for anomaly detection in network security.
problem Understanding and improving anomaly detection in network security.
method Revisit probabilistic PCA model and its connection to MSNM framework.
result Mathematical model connects PCA to MSNM for anomaly detection.
End-to-end learning of codes for secure BPSK communication in Gaussian wiretap channel.
problem Secure communication in the presence of an adversary for BPSK modulation.
method Learning finite-length codes using deep neural networks (DNNs) with mutual information estimation.
result Learned codes achieve near-optimal security performance, as demonstrated by numerical results.
Explores security challenges of machine learning in real-world systems.
problem Vulnerabilities in machine learning models deployed in safety-critical systems.
method Broadens systems security view of ML vulnerabilities, identifies novel challenges, proposes mitigation suggestions.
result Highlights novel challenges and proposes mitigation strategies for securing ML systems.
This study evaluates Algorand and Ethereum 2.0 for blockchain trilemma challenges.
problem Balancing decentralization, security, and scalability in blockchain systems.
method Comparative analysis of Algorand and Ethereum 2.0 using metrics for decentralization, scalability, and security.
result Each system has strengths in addressing the blockchain trilemma, providing insights for other blockchain technologies.
Privacy concern has been increasingly important in many machine learning (ML) problems. We study empirical risk minimization (ERM) problems under secure multi-party computation (MPC) frameworks. Main technical tools for MPC have been developed based on cryptography. One of limitations in current cryptographically priva…
Contextual bandit framework improves revenue optimization in securities lending market.
problem Optimizing revenue for agent lenders in a dynamic securities lending market.
method Utilized contextual bandit frameworks to address dynamic pricing problems in an e-commerce-like securities lending market.
result Contextual bandit approach consistently outperforms traditional methods by at least 15% in total revenue generated.
This research secures deployed sentiment analysis models by identifying and defending against attack vectors.
problem Securing deployed machine learning models, particularly sentiment analysis systems, from adversarial attacks.
method BAD (Build, Attack, Defend) Architecture, evaluating two implementations.
result Demonstrated a viable methodology for securing machine learning models in production.
How secure automatic speaker verification (ASV) technology is? More concretely, given a specific target speaker, how likely is it to find another person who gets falsely accepted as that target? This question may be addressed empirically by studying naturally confusable pairs of speakers within a large enough corpus. T…
Neural Networks (NN) have recently emerged as backbone of several sensitive applications like automobile, medical image, security, etc. NNs inherently offer Partial Fault Tolerance (PFT) in their architecture; however, the biased PFT of NNs can lead to severe consequences in applications like cryptography and security …
Study proposes hybrid machine learning models for crop yield prediction.
problem Crop yield prediction for food security.
method Hybrid machine learning models (ANN-ICA and ANN-GWO).
result ANN-GWO model outperformed ANN-ICA in crop yield prediction.
Recurrent neural networks and sequence to sequence models require a predetermined length for prediction output length. Our model addresses this by allowing the network to predict a variable length output in inference. A new loss function with a tailored gradient computation is developed that trades off prediction accur…
Automatically finds effective security strategies through reinforcement learning and self-play.
problem Finding effective security strategies for intrusion prevention.
method Modeling interaction as a Markov game, evolving attack and defense strategies through reinforcement learning and self-play.
result Effective security strategies emerge from self-play, reflecting common-sense knowledge.
There has been a surge of interest in using machine learning (ML) to automatically detect malware through their dynamic behaviors. These approaches have achieved significant improvement in detection rates and lower false positive rates at large scale compared with traditional malware analysis methods. ML in threat dete…
Securely evaluates the benefits of merging datasets for causal estimation.
problem Challenges in assessing the value of merging datasets for causal treatment effect estimation.
method Cryptographically secure multi-party computation to evaluate Expected Information Gain (EIG) while ensuring privacy.
result Demonstrates the first privacy-preserving method for dataset acquisition tailored to causal estimation.
The DAO Report led to a significant shift of ICO activity to Europe.
problem The impact of U.S. regulatory changes on global ICO activity.
method Analysis of a global dataset of ICOs from 2014 to 2021, focusing on the DAO Report's effects.
result A substantial and persistent reallocation of ICO activity to Europe following the DAO Report.
PrivacyFL simulates privacy-preserving federated learning.
problem Ensuring privacy in federated learning environments.
method Extensible, configurable simulator for federated learning.
result PrivacyFL checks feasibility and improves model accuracy.
Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient fo…
In this paper, we introduce Anomaly Contribution Explainer or ACE, a tool to explain security anomaly detection models in terms of the model features through a regression framework, and its variant, ACE-KL, which highlights the important anomaly contributors. ACE and ACE-KL provide insights in diagnosing which attribut…
This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.
problem Efficiently verifying the robustness of boosted tree ensembles against norm-based attackers.
method Formal verification of robustness for large-spread boosted tree ensembles, considering L∞-norm and pseudo-polynomial time for Lp-norm verification. result Polynomial time verification for L∞-norm attackers, NP-hard for other norms, and pseudo-polynomial time for Lp-norm verification. The article presents a new entropy model for assessing stock market interest.
problem Assessing investor interest and market sentiment in exchange-traded securities.
method Intrinsic entropy model using actual trading data, without exogenous factors.
result Empirical evidence supports the model's ability to predict trading activity.
A new federated learning method protects privacy in mobile crowdsensing.
problem Data and model privacy protection in federated extreme gradient boosting for mobile crowdsensing.
method Secret sharing based federated learning architecture FedXGB.
result FedXGB achieves less than 1% accuracy loss while preserving model privacy.
Quantum computing offers new solutions for financial optimization, pricing, risk, and security.
problem Core financial bottlenecks in combinatorial search, expectation estimation, and rare-event analysis.
method Identify bottlenecks, specify quantum primitives, compare with classical benchmarks, assess under constraints.
result Strongest near-term case for quantum finance in hybrid workflows, constrained search, and amplitude-estimation.
Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers that propose defenses are quickly shown to be incorrect. We believe a large contri…
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.
Safeguarding privacy in machine learning is highly desirable, especially in collaborative studies across many organizations. Privacy-preserving distributed machine learning (based on cryptography) is popular to solve the problem. However, existing cryptographic protocols still incur excess computational overhead. Here,…
Spiking Neural Networks (SNNs) claim to present many advantages in terms of biological plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs). Recent works have shown that DNNs are vulnerable to adversarial attacks, i.e., small perturbations added to the input data can lead to targeted or r…
Secure federated learning reduces privacy risks with differential privacy and secure multiparty computation.
problem Reverse engineering of private client data from federated learning model parameters.
method Combining differential privacy and secure multiparty computation.
result Improved accuracy of shared models without significant privacy loss.
Optimizes a portfolio for an investor preferring accepted securities over a reference security.
problem Investor preference for a set of securities over a reference security with constraints.
method Mean-variance optimization with Sharpe Ratio performance measurement.
result Derives an optimal portfolio that maximizes returns while minimizing risk.
New federated learning protocols resist Byzantine failures and offer privacy guarantees.
problem Resisting Byzantine failures in federated learning.
method Proposes robust federated learning protocols with optimal statistical rates and privacy guarantees.
result Achieves nearly optimal statistical rates and tight rate in terms of all parameters for strongly convex losses.
LightSecAgg reduces secure aggregation complexity in FL.
problem Complexity in secure aggregation protocols for FL systems.
method One-shot aggregate-mask reconstruction via mask encoding/decoding.
result Significantly reduces overhead for resiliency against dropped users.
Proposes a method for private aggregation in heterogeneous federated learning.
problem Ensuring resilience to Byzantine clients and maintaining client data privacy in federated learning with heterogeneous data.
method Careful co-design of verifiable secret sharing, secure aggregation, and private information retrieval scheme.
result Achieves information-theoretic privacy guarantees and Byzantine resilience under data heterogeneity.
Neural networks for stock price prediction often misrepresent model performance due to flawed error metrics.
problem Flawed prediction error metrics lead to unreliable model evaluations in the securities market.
method Used data from 20 stock datasets across multiple markets and evaluated with four prediction error measures.
result Prediction error value only partially reflects model accuracy and fails to represent stock price direction.
Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned system handles correctly. The existence of these errors raises a variety of quest…
Study shows Bitcoin security tied to mining rewards and prices.
problem Understanding Bitcoin security's dependency on market outcomes.
method Used ARDL approach with daily blockchain and Bitcoin data from 2014-2019.
result Bitcoin security outcomes linked to Bitcoin price and mining rewards.
Thanks to the advances in machine learning, data-driven analysis tools have become valuable solutions for various applications. However, there still remain essential challenges to develop effective data-driven methods because of the need to acquire a large amount of data and to have sufficient computing power to handle…
Study evaluates risk in options using volatility surface projections.
problem Risk assessment of options due to their non-linear price behavior and volatility fluctuations.
method Parametric surface projection method for implied volatility.
result Enhanced risk evaluation through dynamic volatility surface analysis.
A pair of points in a riemannian manifold makes a secure configuration if the totality of geodesics connecting them can be blocked by a finite set. The manifold is secure if every configuration is secure. We investigate the security of compact, locally symmetric spaces.
Efficiently preserves privacy in logistic regression for IoT data.
problem Balancing data privacy and utility in collaborative learning.
method Matrix encryption approach for secure multi-party computation.
result Proposes a privacy-preserving logistic regression model with fast convergence.
Our work specifies the fundamental cost of using secure aggregation in federated learning.
problem Training a distributed model with differential privacy constraints.
method Characterized the communication cost required for optimal accuracy under differential privacy, achieved by a linear scheme.
result The fundamental communication cost is $ ilde{O}\left( \min(n^2\varepsilon^2, d)
ight)$ bits per client, both sufficient and necessary.
Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol. However, this process assumes a trusted centralized infrastructure for coordination, and clients must…
Framework for responsible LLM deployment with human involvement and decentralized technologies.
problem Challenges in deploying LLMs for high-stakes decisions, including data security and accountability.
method Interactive human involvement through multiple iterations, decentralized technologies, and automated auditing.
result Enhanced security and accountability in LLM deployment for financial decisions.
New security patch for object tracking in self-driving cars mitigates vulnerabilities.
problem Vulnerability of object tracking in self-driving cars, especially Kalman Filter-based trackers.
method Adaptive strategy to balance focus on observations and predictions based on deviation anomaly index.
result Certified effectiveness against a generalized hijacking attack model.