arXiv subjects

Farinaz Koushanfar

Publications and source records attributed to Farinaz Koushanfar.

At least 55 records · Page 3Linked to original sources

arXiv2024

EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models

This paper introduces EmMark,a novel watermarking framework for protecting the intellectual property (IP) of embedded large language models deployed on resource-constrained edge devices. To address the IP theft risks posed by malicious end-users, EmMark enables proprietors to authenticate ownership by querying the watermarked model weights and matching the inserted signatures. EmMark's novelty lies in its strategic watermark weight parameters selection, nsuring robustness and maintaining model quality. Extensive proof-of-concept evaluations of models from OPT and LLaMA-2 families demonstrate EmMark's fidelity, achieving 100% success in watermark extraction with model performance preservation. EmMark also showcased its resilience against watermark removal and forging attacks.

cs.CR↗

arXiv2023

SPAM: Secure & Private Aircraft Management

With the rising use of aircrafts for operations ranging from disaster-relief to warfare, there is a growing risk of adversarial attacks. Malicious entities often only require the location of the aircraft for these attacks. Current satellite-aircraft communication and tracking protocols put aircrafts at risk if the satellite is compromised, due to computation being done in plaintext. In this work, we present \texttt{SPAM}, a private, secure, and accurate system that allows satellites to efficiently manage and maintain tracking angles for aircraft fleets without learning aircrafts' locations. \texttt{SPAM} is built upon multi-party computation and zero-knowledge proofs to guarantee privacy and high efficiency. While catered towards aircrafts, \texttt{SPAM}'s zero-knowledge fleet management can be easily extended to the IoT, with very little overhead.

cs.CR↗

arXiv2023

Tailor: Altering Skip Connections for Resource-Efficient Inference

Deep neural networks use skip connections to improve training convergence. However, these skip connections are costly in hardware, requiring extra buffers and increasing on- and off-chip memory utilization and bandwidth requirements. In this paper, we show that skip connections can be optimized for hardware when tackled with a hardware-software codesign approach. We argue that while a network's skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware efficient implementation with minimal to no accuracy loss. We introduce Tailor, a codesign tool whose hardware-aware training algorithm gradually removes or shortens a fully trained network's skip connections to lower their hardware cost. Tailor improves resource utilization by up to 34% for BRAMs, 13% for FFs, and 16% for LUTs for on-chip, dataflow-style architectures. Tailor increases performance by 30% and reduces memory bandwidth by 45% for a 2D processing element array architecture.

cs.CV↗

arXiv2023

ZKROWNN: Zero Knowledge Right of Ownership for Neural Networks

Training contemporary AI models requires investment in procuring learning data and computing resources, making the models intellectual property of the owners. Popular model watermarking solutions rely on key input triggers for detection; the keys have to be kept private to prevent discovery, forging, and removal of the hidden signatures. We present ZKROWNN, the first automated end-to-end framework utilizing Zero-Knowledge Proofs (ZKP) that enable an entity to validate their ownership of a model, while preserving the privacy of the watermarks. ZKROWNN permits a third party client to verify model ownership in less than a second, requiring as little as a few KBs of communication.

cs.CR↗

arXiv2023

zPROBE: Zero Peek Robustness Checks for Federated Learning

Privacy-preserving federated learning allows multiple users to jointly train a model with coordination of a central server. The server only learns the final aggregation result, thus the users' (private) training data is not leaked from the individual model updates. However, keeping the individual updates private allows malicious users to perform Byzantine attacks and degrade the accuracy without being detected. Best existing defenses against Byzantine workers rely on robust rank-based statistics, e.g., median, to find malicious updates. However, implementing privacy-preserving rank-based statistics is nontrivial and not scalable in the secure domain, as it requires sorting all individual updates. We establish the first private robustness check that uses high break point rank-based statistics on aggregated model updates. By exploiting randomized clustering, we significantly improve the scalability of our defense without compromising privacy. We leverage our statistical bounds in zero-knowledge proofs to detect and remove malicious updates without revealing the private user updates. Our novel framework, zPROBE, enables Byzantine resilient and secure federated learning. Empirical evaluations demonstrate that zPROBE provides a low overhead solution to defend against state-of-the-art Byzantine attacks while preserving privacy.

cs.LG↗

arXiv2023

FLAME: Taming Backdoors in Federated Learning (Extended Version 1)

Federated Learning (FL) is a collaborative machine learning approach allowing participants to jointly train a model without having to share their private, potentially sensitive local datasets with others. Despite its benefits, FL is vulnerable to backdoor attacks, in which an adversary injects manipulated model updates into the model aggregation process so that the resulting model will provide targeted false predictions for specific adversary-chosen inputs. Proposed defenses against backdoor attacks based on detecting and filtering out malicious model updates consider only very specific and limited attacker models, whereas defenses based on differential privacy-inspired noise injection significantly deteriorate the benign performance of the aggregated model. To address these deficiencies, we introduce FLAME, a defense framework that estimates the sufficient amount of noise to be injected to ensure the elimination of backdoors while maintaining the model performance. To minimize the required amount of noise, FLAME uses a model clustering and weight clipping approach. Our evaluation of FLAME on several datasets stemming from application areas including image classification, word prediction, and IoT intrusion detection demonstrates that FLAME removes backdoors effectively with a negligible impact on the benign performance of the models. Furthermore, following the considerable attention that our research has received after its presentation at USENIX SEC 2022, FLAME has become the subject of numerous investigations proposing diverse attack methodologies in an attempt to circumvent it. As a response to these endeavors, we provide a comprehensive analysis of these attempts. Our findings show that these papers (e.g., 3DFed [36]) have not fully comprehended nor correctly employed the fundamental principles underlying FLAME, i.e., our defense mechanism effectively repels these attempted attacks.

cs.CR↗

arXiv2023

Secure and Trustworthy Computing 2.0 Vision Statement

The Secure and Trustworthy Computing (SaTC) program within the National Science Foundation (NSF) program serves as the primary instrument for creating novel fundamental science in security and privacy in the United States with broad impacts that influence the world. The program funds research in a vast array of research topics that span technology, theory, policy, law, and society. In the Spring of 2023, the program managers of SaTC requested that the community prepare a vision for the next ten years of research. This document represents the results of that effort which involved collecting input from numerous members of the security and privacy community, industry, academics, and government. Assembled from that input, this document offers a comprehensive view of general themes and specific areas of focus for future research as envisioned by the community.

cs.CR↗

arXiv2023

G-Scan: Graph Neural Networks for Line-Level Vulnerability Identification in Smart Contracts

Due to the immutable and decentralized nature of Ethereum (ETH) platform, smart contracts are prone to security risks that can result in financial loss. While existing machine learning-based vulnerability detection algorithms achieve high accuracy at the contract level, they require developers to manually inspect source code to locate bugs. To this end, we present G-Scan, the first end-to-end fine-grained line-level vulnerability detection system evaluated on the first-of-its-kind real world dataset. G-Scan first converts smart contracts to code graphs in a dependency and hierarchy preserving manner. Next, we train a graph neural network to identify vulnerable nodes and assess security risks. Finally, the code graphs with node vulnerability predictions are mapped back to the smart contracts for line-level localization. We train and evaluate G-Scan on a collected real world smart contracts dataset with line-level annotations on reentrancy vulnerability, one of the most common and severe types of smart contract vulnerabilities. With the well-designed graph representation and high-quality dataset, G-Scan achieves 93.02% F1-score in contract-level vulnerability detection and 93.69% F1-score in line-level vulnerability localization. Additionally, the lightweight graph neural network enables G-Scan to localize vulnerabilities in 6.1k lines of code smart contract within 1.2 seconds.

cs.CR↗

arXiv2023

Adversarial Scratches: Deployable Attacks to CNN Classifiers

A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model's input which lead to incorrect predictions. Unfortunately, most literature focuses on visually imperceivable perturbations to be applied to digital images that often are, by design, impossible to be deployed to physical targets. We present Adversarial Scratches: a novel L0 black-box attack, which takes the form of scratches in images, and which possesses much greater deployability than other state-of-the-art attacks. Adversarial Scratches leverage Bézier Curves to reduce the dimension of the search space and possibly constrain the attack to a specific location. We test Adversarial Scratches in several scenarios, including a publicly available API and images of traffic signs. Results show that, often, our attack achieves higher fooling rate than other deployable state-of-the-art methods, while requiring significantly fewer queries and modifying very few pixels.

cs.LG↗

arXiv2023

NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression

Video compression plays a significant role in IoT devices for the efficient transport of visual data while satisfying all underlying bandwidth constraints. Deep learning-based video compression methods are rapidly replacing traditional algorithms and providing state-of-the-art results on edge devices. However, recently developed adversarial attacks demonstrate that digitally crafted perturbations can break the Rate-Distortion relationship of video compression. In this work, we present a real-world LED attack to target video compression frameworks. Our physically realizable attack, dubbed NetFlick, can degrade the spatio-temporal correlation between successive frames by injecting flickering temporal perturbations. In addition, we propose universal perturbations that can downgrade performance of incoming video without prior knowledge of the contents. Experimental results demonstrate that NetFlick can successfully deteriorate the performance of video compression frameworks in both digital- and physical-settings and can be further extended to attack downstream video classification networks.

eess.IV↗

arXiv2023

Trustworthy AI Inference Systems: An Industry Research View

In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized inferences to aid their decision, while at the same time utilizing appropriate security protection mechanisms for AI models. Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time. To approach the subject, we start by introducing current trends in AI inference systems. We continue by elaborating on the relationship between Intellectual Property (IP) and private data protection in such systems. Regarding the protection mechanisms, we survey the security and privacy building blocks instrumental in designing, building, deploying, and operating private AI inference systems. For example, we highlight opportunities and challenges in AI systems using trusted execution environments combined with more recent advances in cryptographic techniques to protect data in use. Finally, we outline areas of further development that require the global collective attention of industry, academia, and government researchers to sustain the operation of trustworthy AI inference systems.

cs.CR↗

arXiv2022

RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression

Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial attacks on deep learning-based video compression and downstream classification systems. Our attack framework, dubbed RoVISQ, manipulates the Rate-Distortion ($\textit{R}$-$\textit{D}$) relationship of a video compression model to achieve one or both of the following goals: (1) increasing the network bandwidth, (2) degrading the video quality for end-users. We further devise new objectives for targeted and untargeted attacks to a downstream video classification service. Finally, we design an input-invariant perturbation that universally disrupts video compression and classification systems in real time. Unlike previously proposed attacks on video classification, our adversarial perturbations are the first to withstand compression. We empirically show the resilience of RoVISQ attacks against various defenses, i.e., adversarial training, video denoising, and JPEG compression. Our extensive experimental results on various video datasets show RoVISQ attacks deteriorate peak signal-to-noise ratio by up to 5.6dB and the bit-rate by up to $\sim$ 2.4$\times$ while achieving over 90$\%$ attack success rate on a downstream classifier. Our user study further demonstrates the effect of RoVISQ attacks on users' QoE.

cs.CV↗

arXiv2022

LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models

The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints like peak memory utilization and latency is non-trivial. This is exacerbated by the proliferation of various hardware. We leverage the somewhat surprising empirical observation that the number of decoder parameters in autoregressive Transformers has a high rank correlation with task performance, irrespective of the architecture topology. This observation organically induces a simple Neural Architecture Search (NAS) algorithm that uses decoder parameters as a proxy for perplexity without need for any model training. The search phase of our training-free algorithm, dubbed Lightweight Transformer Search (LTS), can be run directly on target devices since it does not require GPUs. Using on-target-device measurements, LTS extracts the Pareto-frontier of perplexity versus any hardware performance cost. We evaluate LTS on diverse devices from ARM CPUs to NVIDIA GPUs and two popular autoregressive Transformer backbones: GPT-2 and Transformer-XL. Results show that the perplexity of 16-layer GPT-2 and Transformer-XL can be achieved with up to 1.5x, 2.5x faster runtime and 1.2x, 2.0x lower peak memory utilization. When evaluated in zero and one-shot settings, LTS Pareto-frontier models achieve higher average accuracy compared to the 350M parameter OPT across 14 tasks, with up to 1.6x lower latency. LTS extracts the Pareto-frontier in under 3 hours while running on a commodity laptop. We effectively remove the carbon footprint of hundreds of GPU hours of training during search, offering a strong simple baseline for future NAS methods in autoregressive language modeling.

cs.LG↗

arXiv2022

FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAs

Steganography and digital watermarking are the tasks of hiding recoverable data in image pixels. Deep neural network (DNN) based image steganography and watermarking techniques are quickly replacing traditional hand-engineered pipelines. DNN based watermarking techniques have drastically improved the message capacity, imperceptibility and robustness of the embedded watermarks. However, this improvement comes at the cost of increased computational overhead of the watermark encoder neural network. In this work, we design the first accelerator platform FastStamp to perform DNN based steganography and digital watermarking of images on hardware. We first propose a parameter efficient DNN model for embedding recoverable bit-strings in image pixels. Our proposed model can match the success metrics of prior state-of-the-art DNN based watermarking methods while being significantly faster and lighter in terms of memory footprint. We then design an FPGA based accelerator framework to further improve the model throughput and power consumption by leveraging data parallelism and customized computation paths. FastStamp allows embedding hardware signatures into images to establish media authenticity and ownership of digital media. Our best design achieves 68 times faster inference as compared to GPU implementations of prior DNN based watermark encoder while consuming less power.

cs.CV↗

arXiv2022

Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers

Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based language models to classify input texts. However, there is a lack of systematic study on how much private information can be inverted when publishing models. In this paper, we formulate \emph{Text Revealer} -- the first model inversion attack for text reconstruction against text classification with transformers. Our attacks faithfully reconstruct private texts included in training data with access to the target model. We leverage an external dataset and GPT-2 to generate the target domain-like fluent text, and then perturb its hidden state optimally with the feedback from the target model. Our extensive experiments demonstrate that our attacks are effective for datasets with different text lengths and can reconstruct private texts with accuracy.

cs.CL↗

arXiv2022

PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications

Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks. Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and is activated by the trigger in the input space. The increasing deployment of DNNs in critical systems and the surge of outsourcing DNN training (which makes Trojan attack easier) makes the detection of Trojan attacks necessary. While Neural Trojan detection has been studied in the image domain, there is a lack of solutions in the NLP domain. In this paper, we propose a model-level Trojan detection framework by analyzing the deviation of the model output when we introduce a specially crafted perturbation to the input. Particularly, we extract the model's responses to perturbed inputs as the `signature' of the model and train a meta-classifier to determine if a model is Trojaned based on its signature. We demonstrate the effectiveness of our proposed method on both a dataset of NLP models we create and a public dataset of Trojaned NLP models from TrojAI. Furthermore, we propose a lightweight variant of our detection method that reduces the detection time while preserving the detection rates.

cs.LG↗

arXiv2022

Abusing Commodity DRAMs in IoT Devices to Remotely Spy on Temperature

The ubiquity and pervasiveness of modern Internet of Things (IoT) devices opens up vast possibilities for novel applications, but simultaneously also allows spying on, and collecting data from, unsuspecting users to a previously unseen extent. This paper details a new attack form in this vein, in which the decay properties of widespread, off-the-shelf DRAM modules are exploited to accurately sense the temperature in the vicinity of the DRAM-carrying device. Among others, this enables adversaries to remotely and purely digitally spy on personal behavior in users' private homes, or to collect security-critical data in server farms, cloud storage centers, or commercial production lines. We demonstrate that our attack can be performed by merely compromising the software of an IoT device and does not require hardware modifications or physical access at attack time. It can achieve temperature resolutions of up to 0.5°C over a range of 0°C to 70°C in practice. Perhaps most interestingly, it even works in devices that do not have a dedicated temperature sensor on board. To complete our work, we discuss practical attack scenarios as well as possible countermeasures against our temperature espionage attacks.

cs.CR↗

arXiv2022

ReFace: Real-time Adversarial Attacks on Face Recognition Systems

Deep neural network based face recognition models have been shown to be vulnerable to adversarial examples. However, many of the past attacks require the adversary to solve an input-dependent optimization problem using gradient descent which makes the attack impractical in real-time. These adversarial examples are also tightly coupled to the attacked model and are not as successful in transferring to different models. In this work, we propose ReFace, a real-time, highly-transferable attack on face recognition models based on Adversarial Transformation Networks (ATNs). ATNs model adversarial example generation as a feed-forward neural network. We find that the white-box attack success rate of a pure U-Net ATN falls substantially short of gradient-based attacks like PGD on large face recognition datasets. We therefore propose a new architecture for ATNs that closes this gap while maintaining a 10000x speedup over PGD. Furthermore, we find that at a given perturbation magnitude, our ATN adversarial perturbations are more effective in transferring to new face recognition models than PGD. ReFace attacks can successfully deceive commercial face recognition services in a transfer attack setting and reduce face identification accuracy from 82% to 16.4% for AWS SearchFaces API and Azure face verification accuracy from 91% to 50.1%.

cs.CV↗