Adapting deep learning for object detection to detect mixed image tampering.
problem Detecting mixed image tampering without prior knowledge of the method.
method Adapting deep learning for object detection to learn from a large database of various image types, using a Multi-stream Faster RCNN network with fused features from ELA and BAG error maps.
result Improved accuracy in detecting mixed image tampering.
We investigate the problem of reliable communication between two legitimate parties over deletion channels under an active eavesdropping (aka jamming) adversarial model. To this goal, we develop a theoretical framework based on probabilistic finite-state automata to define novel encoding and decoding schemes that ensur…
Tampering data during training can corrupt neural networks, leading to misclassification.
problem Adversarial attacks on neural networks during training.
method Creating a backdoor in neural networks by modifying training data.
result A single pixel modification to all images of a class in training data can corrupt neural networks, leading to misclassification.
New algorithm rSVDdpd improves robustness and scalability for video surveillance background modeling.
problem Camera tampering and noisy videos make background separation challenging.
method Introduces rSVDdpd, a robust singular value decomposition technique for scalable video surveillance.
result Demonstrates superior performance on benchmark and real-life datasets.
DeFi TrustBoost uses blockchain and AI to assess small business loans.
problem Assessing small business loans from low-wealth households.
method Combines blockchain and Explainable AI to ensure confidentiality, compliance, and security.
result Tamper-proof auditing and on-chain/off-chain data storage for financial organizations.
New method detects adversarial images by exploiting their density.
problem Detecting adversarial images that are hard to find with gradient methods.
method Develop a test based on the density of adversarial directions.
result Unprecedented accuracy in detecting adversarial attacks under white-box setting.
Defends against strategic data manipulation in machine learning.
problem Adversaries can tamper with datasets to influence learning outcomes.
method Uses multiple learners and strategic activation to counteract attacks.
result Demonstrates effectiveness of a game-theoretic approach to defense.
Blockchain is a distributed database that keeps a chronologically-growing list (chain) of records (blocks) secure from tampering and revision. While computerisation has changed the nature of a ledger from clay tables in the old days to digital records in modern days, blockchain technology is the first true innovation i…
CheckNet verifies neural network inference on untrusted devices.
problem Ensuring secure and tamper-proof inference on untrusted devices.
method A checksum-based approach for neural network inference verification.
result Excellent attack detection and success bounds on various models.
Recent changes to greenhouse gas emission policies are catalyzing the electric vehicle (EV) market making it readily accessible to consumers. While there are challenges that arise with dense deployment of EVs, one of the major future concerns is cyber security threat. In this paper, cyber security threats in the form o…
Post-Quantum Secure Federated DeFi for Inclusive Banking
problem Financial systems and DeFi ecosystems are vulnerable to quantum computing threats.
method Post-Quantum Secure Federated DeFi framework using lattice-based FHE.
result End-to-end homomorphic computation enables inter-bank collaboration.
It is usual to consider data protection and learnability as conflicting objectives. This is not always the case: we show how to jointly control inference --- seen as the attack --- and learnability by a noise-free process that mixes training examples, the Crossover Process (cp). One key point is that the cp~is typicall…
HMN detects fake faces using memory networks and visual cues.
problem Detecting fake faces from unseen manipulation types.
method Hierarchical Memory Network (HMN) architecture.
result Superior performance in fake and fraudulent face detection.
Paper proposes a SIMO DNN for indoor localization using Wi-Fi fingerprints.
problem Indoor localization with high accuracy and efficiency.
method Single-input and multi-output deep neural network architecture.
result SIMO-DNN scheme outperforms existing methods in floor detection and location accuracy.
Paper proposes real-time risk metrics for stablecoin protocols.
problem Lack of risk management frameworks for stablecoins.
method Developed two risk metrics: capitalization and liquidity.
result Demonstrated practical benefits of real-time on-chain data.
New method for robust PCA with exponential family distributions.
problem Recovering low-rank structure from data matrices with outliers.
method Alternating Direction Method of Multipliers for eextRPCA. result Demonstrated effectiveness in steel sheet defect detection and crime activity monitoring.
Study finds Aave token network has core-periphery structure, with high decentralization predicting better returns.
problem Understanding the actual decentralization in DeFi token transactions on the Ethereum blockchain.
method Applied social network analysis to measure decentralization in Aave token transactions.
result A more decentralized Aave token network predicts higher returns and lower volatility.
FedCoin uses blockchain to fairly distribute incentives in federated learning.
problem Fairly incentivizing data owners in federated learning with privacy concerns.
method FedCoin uses a blockchain-based peer-to-peer payment system with a proof of Shapley (PoSap) protocol to calculate and distribute Shapley Values.
result FedCoin accurately computes Shapley Values and promotes high-quality data contributions.
Many traditional methods for identifying changepoints can struggle in the presence of outliers, or when the noise is heavy-tailed. Often they will infer additional changepoints in order to fit the outliers. To overcome this problem, data often needs to be pre-processed to remove outliers, though this is difficult for a…
FOCUS addresses label quality disparity in FL for healthcare applications.
problem Label quality disparity in federated learning for healthcare applications.
method FOCUS maintains a small set of benchmark samples and computes the mutual cross-entropy between local and benchmark datasets to quantify label credibility. It then adjusts client weights based on credibility values.
result FOCUS effectively reduces the impact of noisy labels from clients, improving model performance.
Proposes using mode connectivity to improve adversarial robustness of neural networks.
problem Improving adversarial robustness of deep neural networks.
method Employing mode connectivity in loss landscapes to study adversarial robustness and propose methods for improvement.
result Path connection learned using limited bonafide data can effectively mitigate adversarial effects while maintaining original accuracy.
New algorithm finds corrupted vertices in graphs with few queries.
problem Adversarial tampering of graph edges and vertices.
method Active learning algorithm with polynomial query complexity.
result Efficiently recovers corrupted vertices with small query complexity.
Paper detects Trojan neural networks with limited or no data.
problem Robustness of DNNs against Trojan attacks in data-scarce scenarios.
method Proposes data-limited and data-free TrojanNet detectors.
result Demonstrates effectiveness of detectors on various datasets.
Study blockchain's impact on primary financial market challenges.
problem Challenges of blockchain in securities issuance and trading.
method Hybrid method combining interviews and surveys.
result Complex due diligence, mismatch, and difficult monitoring are significant challenges.
FaceSigns embeds a secret watermark in images to authenticate and detect deepfakes.
problem Realistic image and video manipulation threats, especially deepfakes.
method Semi-fragile watermarking using neural networks, robust to face-swapping but fragile to deepfake manipulations.
result FaceSigns can reliably detect deepfake content with high accuracy.
New findings show strong barriers against computational robustness in adversarial learning.
problem Computational robustness of classifiers against adversarial attacks.
method Information-theoretic and computational proofs for evasion and poisoning attacks.
result Polynomial-time attacks can find adversarial examples of O(√n) Hamming distance for product distributions.
Study shows adversarial attacks are more likely when test instances are concentrated, leading to vulnerabilities in robust classifiers.
problem Adversarial attacks on robust classifiers when test instances are concentrated.
method Theoretical study linking concentration of measure to adversarial vulnerability, focusing on Levy families and product spaces.
result Adversarial attacks can be made effective with minimal perturbations when test instances are concentrated.