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.
VarDetect monitors API queries to detect model extraction attacks.
In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the underlying learning task, and *fidelity*, i.e., matching the predictions of the r…
Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, suc…
Marich extracts high-fidelity models from public data with minimal queries.
Paper presents first model extraction attack against DRL models.
This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies. Recent research have established the vulnerability of supervised machine learning models (e.g., classifiers) to model extraction attacks. Such attacks leverage the loosely-restricte…
This work formalizes and solves GNN extraction, a new type of attack.
Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service ("predictive analytics") systems are an example: Some …
Attack reveals model details from counterfactual explanations.
Paper improves privacy for language models against reconstruction attacks.
In Machine Learning as a Service, a provider trains a deep neural network and gives many users access. The hosted (source) model is susceptible to model stealing attacks, where an adversary derives a surrogate model from API access to the source model. For post hoc detection of such attacks, the provider needs a robust…
Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their training dataset. While some model inversion attacks have been developed in the past in the black-box attack setting, in which the adversary does …
Recently, machine learning (ML) has introduced advanced solutions to many domains. Since ML models provide business advantage to model owners, protecting intellectual property of ML models has emerged as an important consideration. Confidentiality of ML models can be protected by exposing them to clients only via predi…
We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the impo…
Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy attacks. In this work we demonstrate how model inversion attacks, extracting trai…
Paper proposes a method to improve building extraction from aerial images by adapting CNN models.
CEGA addresses GNN security by enabling cost-effective model acquisition.
This paper optimizes liquidation strategies in DeFi protocols to prevent MEV attacks.
Entangled watermarks improve model defense against extraction attacks.
Maximal extractable value in CFMMs can degrade or improve routing quality, with reordering MEV showing logarithmic impact.
The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their rob…
Poisoning datasets can reveal private details of other users' training points.
It is well known that speaker verification systems are subject to spoofing attacks. The Automatic Speaker Verification Spoofing and Countermeasures Challenge -- ASVSpoof2015 -- provides a standard spoofing database, containing attacks based on synthetic speech, along with a protocol for experiments. This paper describe…
New method improves blackbox attack transferability by perturbing feature hierarchy.
This paper examines MEV attacks in dynamic AMMs and proposes new protections.
Regularization helps protect machine learning models from poisoning attacks.
Robust ASR model removes fast-changing features to resist attacks.
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks perturbing the raw input spaces may fail to capture structural information hidden in t…
Interpreting machine learning models helps understand adversarial attacks and defenses.
UM-GNN improves GNN robustness against poisoning attacks.
Deep learning detects APT attacks with high accuracy and low false positives.
Paper proposes a method to generate adversarial perturbations for black-box attacks without accessing inner states.
Zeroth-order optimization is an important research topic in machine learning. In recent years, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms rarely extract second-order information of the model function. In this…
Adds layers to NNs to protect them from reverse engineering.
Low-rate application layer distributed denial of service (LDDoS) attacks are both powerful and stealthy. They force vulnerable webservers to open all available connections to the adversary, denying resources to real users. Mitigation advice focuses on solutions that potentially degrade quality of service for legitimate…
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms to extract valuable information from data and produce accurate predictions, it ha…
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the safety of machine learning models since the adversarial attacks can fool such model…
Modeling DEX liquidity with heterogeneous LPs and MEV bots.
Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction attacks, in which an adversary extracts an approximation of MLaaS models by making bla…
Improved RA detection with SNN outperforming baseline by 26.8% EER.
Recent advances in learning Deep Neural Network (DNN) architectures have received a great deal of attention due to their ability to outperform state-of-the-art classifiers across a wide range of applications, with little or no feature engineering. In this paper, we broadly study the applicability of deep learning to we…
Training machine learning (ML) models is expensive in terms of computational power, amounts of labeled data and human expertise. Thus, ML models constitute intellectual property (IP) and business value for their owners. Embedding digital watermarks during model training allows a model owner to later identify their mode…
This paper presents the Speech Technology Center (STC) replay attack detection systems proposed for Automatic Speaker Verification Spoofing and Countermeasures Challenge 2017. In this study we focused on comparison of different spoofing detection approaches. These were GMM based methods, high level features extraction …
A new method transfers adversarial robustness from teacher to student using feature distillation.
Enhances 2D face recognition with 3D features using active illumination.
Common privacy enhancing technologies fail to effectively hide certain statistical aspects of encrypted traffic, namely individual packets length, packets direction and, packets timing. Recent researches have shown that using such attributes, an adversary is able to extract various information from the encrypted traffi…
Machine Learning improves cybersecurity by detecting cyber attacks.
Automatic speaker verification, like every other biometric system, is vulnerable to spoofing attacks. Using only a few minutes of recorded voice of a genuine client of a speaker verification system, attackers can develop a variety of spoofing attacks that might trick such systems. Detecting these attacks using the audi…