Search Results for author:
Found 63 papers, 17 papers with code
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts.
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.
LayerCollapse: Adaptive compression of neural networks
Handling the ever-increasing scale of contemporary deep learning and transformer-based models poses a significant challenge.
LiveTune: Dynamic Parameter Tuning for Feedback-Driven Optimization
Extensive evaluations of our framework on standard machine learning training pipelines show saving up to 60 seconds and 5. 4 Kilojoules of energy per hyperparameter change.
Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems
Machine Learning (ML) has been instrumental in enabling joint transceiver optimization by merging all physical layer blocks of the end-to-end wireless communication systems.
REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models
We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts generated by large language models (LLMs).
SelfVC: Voice Conversion With Iterative Refinement using Self Transformations
In this work, instead of explicitly disentangling attributes with loss terms, we present a framework to train a controllable voice conversion model on entangled speech representations derived from self-supervised learning (SSL) and speaker verification models.
SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection
We theoretically prove the robustness of our algorithm against data and model poisoning attacks in a decentralized linear regression setting.
NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression
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.
Tailor: Altering Skip Connections for Resource-Efficient Inference
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.
FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAs
In this work, we design the first accelerator platform FastStamp to perform DNN based steganography and digital watermarking of images on hardware.
Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers
Our attacks faithfully reconstruct private texts included in training data with access to the target model.
PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications
Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks.
zPROBE: Zero Peek Robustness Checks for Federated Learning
However, keeping the individual updates private allows malicious users to perform Byzantine attacks and degrade the accuracy without being detected.
ReFace: Real-time Adversarial Attacks on Face Recognition Systems
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.
Adversarial Scratches: Deployable Attacks to CNN Classifiers
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.
AdaTest:Reinforcement Learning and Adaptive Sampling for On-chip Hardware Trojan Detection
This paper proposes AdaTest, a novel adaptive test pattern generation framework for efficient and reliable Hardware Trojan (HT) detection.
An Adaptive Black-box Backdoor Detection Method for Deep Neural Networks
Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical diagnosis and autonomous driving.
FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes
We demonstrate that FaceSigns can embed a 128 bit secret as an imperceptible image watermark that can be recovered with a high bit recovery accuracy at several compression levels, while being non-recoverable when unseen Deepfake manipulations are applied.
RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression
In this paper, we conduct the first systematic study for adversarial attacks on deep learning-based video compression and downstream classification systems.
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models
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.
Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection
The goal of federated learning (FL) is to train one global model by aggregating model parameters updated independently on edge devices without accessing users' private data.
Machine Learning-Assisted E-jet Printing of Organic Flexible Biosensors
Electrohydrodynamic-jet (e-jet) printing technique enables the high-resolution printing of complex soft electronic devices.
HASHTAG: Hash Signatures for Online Detection of Fault-Injection Attacks on Deep Neural Networks
We propose HASHTAG, the first framework that enables high-accuracy detection of fault-injection attacks on Deep Neural Networks (DNNs) with provable bounds on detection performance.
Trojan Signatures in DNN Weights
Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model correctly classifies all standard inputs, but generates a targeted, incorrect classification on any input which contains the trigger.
Unsupervised Information Obfuscation for Split Inference of Neural Networks
In our method, the edge device runs the model up to a split layer determined based on its computational capacity.
ESCORT: Ethereum Smart COntRacTs Vulnerability Detection using Deep Neural Network and Transfer Learning
When extended to new vulnerability types, ESCORT yields an average F1-score of 93%.
WaveGuard: Understanding and Mitigating Audio Adversarial Examples
There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Cross-modal Adversarial Reprogramming
Recent works on adversarial reprogramming have shown that it is possible to repurpose neural networks for alternate tasks without modifying the network architecture or parameters.
TAD: Trigger Approximation based Black-box Trojan Detection for AI
While DNNs are widely employed in security-sensitive fields, they are identified to be vulnerable to Neural Trojan (NT) attacks that are controlled and activated by the stealthy trigger.
Expressive Neural Voice Cloning
In this work, we propose a controllable voice cloning method that allows fine-grained control over various style aspects of the synthesized speech for an unseen speaker.
ProFlip: Targeted Trojan Attack With Progressive Bit Flips
In this work, we present ProFlip, the first targeted Trojan attack framework that can divert the prediction of the DNN to the target class by progressively identifying and flipping a small set of bits in model parameters.
A Singular Value Perspective on Model Robustness
Convolutional Neural Networks (CNNs) have made significant progress on several computer vision benchmarks, but are fraught with numerous non-human biases such as vulnerability to adversarial samples.
CLEANN: Accelerated Trojan Shield for Embedded Neural Networks
We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications.
Trustworthy AI Inference Systems: An Industry Research View
Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time.
GeneCAI: Genetic Evolution for Acquiring Compact AI
In the contemporary big data realm, Deep Neural Networks (DNNs) are evolving towards more complex architectures to achieve higher inference accuracy.
SynFi: Automatic Synthetic Fingerprint Generation
Authentication and identification methods based on human fingerprints are ubiquitous in several systems ranging from government organizations to consumer products.
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before.
FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA
While WaveNet produces state-of-the art audio generation results, the naive inference implementation is quite slow; it takes a few minutes to generate just one second of audio on a high-end GPU.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
Principal Component Properties of Adversarial Samples
Deep Neural Networks for image classification have been found to be vulnerable to adversarial samples, which consist of sub-perceptual noise added to a benign image that can easily fool trained neural networks, posing a significant risk to their commercial deployment.
Scratch that! An Evolution-based Adversarial Attack against Neural Networks
We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on an image.
Coda: An End-to-End Neural Program Decompiler
Furthermore, Coda outperforms the sequence-to-sequence model with attention by a margin of 70% program accuracy.
ASCAI: Adaptive Sampling for acquiring Compact AI
This paper introduces ASCAI, a novel adaptive sampling methodology that can learn how to effectively compress Deep Neural Networks (DNNs) for accelerated inference on resource-constrained platforms.
A Neural-based Program Decompiler
Reverse engineering of binary executables is a critical problem in the computer security domain.
Decentralized Bayesian Learning over Graphs
The proposed algorithm can be viewed as a Bayesian and peer-to-peer variant of federated learning in which each agent keeps a "posterior probability distribution" over a global model parameters.
Universal Adversarial Perturbations for Speech Recognition Systems
In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
BlackMarks: Black-box Multi-bit Watermarking for Deep Neural Networks
To extract the WM, BlackMarks queries the model with the WM key images and decodes the owner’s signature from the corresponding predictions using the designed encoding scheme.
SWNet: Small-World Neural Networks and Rapid Convergence
This transformation leverages our important observation that for a set level of accuracy, convergence is fastest when network topology reaches the boundary of a Small-World Network.
Peer-to-peer Federated Learning on Graphs
We consider the problem of training a machine learning model over a network of nodes in a fully decentralized framework.
CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNs
CodeX incorporates nonlinear encoding to the computation flow of neural networks to save memory.
Adversarial Reprogramming of Text Classification Neural Networks
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network.
RAPIDNN: In-Memory Deep Neural Network Acceleration Framework
To enable in-memory processing, RAPIDNN reinterprets a DNN model and maps it into a specialized accelerator, which is designed using non-volatile memory blocks that model four fundamental DNN operations, i. e., multiplication, addition, activation functions, and pooling.
AgileNet: Lightweight Dictionary-based Few-shot Learning
The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time.
DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models
The resulting models are therefore considered to be the IP of the model builder and need to be protected to preserve the owner's competitive advantage.
Cryptography and Security
Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications
Chameleon departs from the common assumption of additive or linear secret sharing models where three or more parties need to communicate in the online phase: the framework allows two parties with private inputs to communicate in the online phase under the assumption of a third node generating correlated randomness in an offline phase.
Towards Safe Deep Learning: Unsupervised Defense Against Generic Adversarial Attacks
We introduce a novel automated countermeasure called Parallel Checkpointing Learners (PCL) to thwart the potential adversarial attacks and significantly improve the reliability (safety) of a victim DL model.
ResBinNet: Residual Binary Neural Network
Recent efforts on training light-weight binary neural networks offer promising execution/memory efficiency.
ReBNet: Residual Binarized Neural Network
We show that the state-of-the-art methods for optimizing binary networks accuracy, significantly increase the implementation cost and complexity.
DeepFense: Online Accelerated Defense Against Adversarial Deep Learning
Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems.
DeepSecure: Scalable Provably-Secure Deep Learning
This paper proposes DeepSecure, a novel framework that enables scalable execution of the state-of-the-art Deep Learning (DL) models in a privacy-preserving setting.
Cryptography and Security
Sub-Linear Privacy-Preserving Near-Neighbor Search
In Near-Neighbor Search (NNS), a new client queries a database (held by a server) for the most similar data (near-neighbors) given a certain similarity metric.
RankMap: A Platform-Aware Framework for Distributed Learning from Dense Datasets
This paper introduces RankMap, a platform-aware end-to-end framework for efficient execution of a broad class of iterative learning algorithms for massive and dense datasets.
