Exploiting Logic Locking for a Neural Trojan Attack on Machine Learning Accelerators

• URL: http://arxiv.org/abs/2304.06017v2
• Date: Fri, 14 Apr 2023 20:52:23 GMT
• Title: Exploiting Logic Locking for a Neural Trojan Attack on Machine Learning Accelerators
• Authors: Hongye Xu, Dongfang Liu, Cory Merkel, Michael Zuzak
• Abstract summary: We show how logic locking can be used to compromise the security of a neural accelerator it protects. Specifically, we show how the deterministic errors caused by incorrect keys can be harnessed to produce neural-trojan-style backdoors.
• Score: 4.605674633999923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Logic locking has been proposed to safeguard intellectual property (IP) during chip fabrication. Logic locking techniques protect hardware IP by making a subset of combinational modules in a design dependent on a secret key that is withheld from untrusted parties. If an incorrect secret key is used, a set of deterministic errors is produced in locked modules, restricting unauthorized use. A common target for logic locking is neural accelerators, especially as machine-learning-as-a-service becomes more prevalent. In this work, we explore how logic locking can be used to compromise the security of a neural accelerator it protects. Specifically, we show how the deterministic errors caused by incorrect keys can be harnessed to produce neural-trojan-style backdoors. To do so, we first outline a motivational attack scenario where a carefully chosen incorrect key, which we call a trojan key, produces misclassifications for an attacker-specified input class in a locked accelerator. We then develop a theoretically-robust attack methodology to automatically identify trojan keys. To evaluate this attack, we launch it on several locked accelerators. In our largest benchmark accelerator, our attack identified a trojan key that caused a 74\% decrease in classification accuracy for attacker-specified trigger inputs, while degrading accuracy by only 1.7\% for other inputs on average.

Related papers

• LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning [49.174341192722615]
  Backdoor attack poses a significant security threat to Deep Learning applications. Recent papers have introduced attacks using sample-specific invisible triggers crafted through special transformation functions. We introduce a novel backdoor attack LOTUS to address both evasiveness and resilience.
  arXiv  Detail & Related papers  (2024-03-25T21:01:29Z)
• LIPSTICK: Corruptibility-Aware and Explainable Graph Neural Network-based Oracle-Less Attack on Logic Locking [1.104960878651584]
  We develop, train, and test a corruptibility-aware graph neural network-based oracle-less attack on logic locking. Our model is explainable in the sense that we analyze what the machine learning model has interpreted in the training process and how it can perform a successful attack.
  arXiv  Detail & Related papers  (2024-02-06T18:42:51Z)
• Does Few-shot Learning Suffer from Backdoor Attacks? [63.9864247424967]
  We show that few-shot learning can still be vulnerable to backdoor attacks. Our method demonstrates a high Attack Success Rate (ASR) in FSL tasks with different few-shot learning paradigms. This study reveals that few-shot learning still suffers from backdoor attacks, and its security should be given attention.
  arXiv  Detail & Related papers  (2023-12-31T06:43:36Z)
• Attention-Enhancing Backdoor Attacks Against BERT-based Models [54.070555070629105]
  Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. We propose a novel Trojan Attention Loss (TAL) which enhances the Trojan behavior by directly manipulating the attention patterns.
  arXiv  Detail & Related papers  (2023-10-23T01:24:56Z)
• Evil from Within: Machine Learning Backdoors through Hardware Trojans [72.99519529521919]
  Backdoors pose a serious threat to machine learning, as they can compromise the integrity of security-critical systems, such as self-driving cars. We introduce a backdoor attack that completely resides within a common hardware accelerator for machine learning. We demonstrate the practical feasibility of our attack by implanting our hardware trojan into the Xilinx Vitis AI DPU.
  arXiv  Detail & Related papers  (2023-04-17T16:24:48Z)
• Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning [7.3007220721129364]
  ML models that contain a backdoor are called Trojan models. Current single-target backdoor attacks require one trigger per target class. We introduce a new, more general attack that will enable a single trigger to result in misclassification to more than one target class.
  arXiv  Detail & Related papers  (2022-03-25T02:54:27Z)
• An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks [0.0]
  The vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. This article proposes a defense algorithm that utilizes the combination of an auto-encoder and block-switching architecture.
  arXiv  Detail & Related papers  (2022-03-11T10:58:24Z)
• Deceptive Logic Locking for Hardware Integrity Protection against Machine Learning Attacks [0.6868387710209244]
  We present a theoretical model to test locking schemes for key-related structural leakage that can be exploited by machine learning. We introduce D-MUX: a deceptive multiplexer-based logic-locking scheme that is resilient against structure-exploiting machine learning attacks. To the best of our knowledge, D-MUX is the first machine-learning-resilient locking scheme capable of protecting against all known learning-based attacks.
  arXiv  Detail & Related papers  (2021-07-19T09:08:14Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• Challenging the Security of Logic Locking Schemes in the Era of Deep Learning: A Neuroevolutionary Approach [0.2982610402087727]
  Deep learning is being introduced in the domain of logic locking. We present SnapShot: a novel attack on logic locking that is the first of its kind to utilize artificial neural networks. We show that SnapShot achieves an average key prediction accuracy of 82.60% for the selected attack scenario.
  arXiv  Detail & Related papers  (2020-11-20T13:03:19Z)
• An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks [59.42357806777537]
  trojan attack aims to attack deployed deep neural networks (DNNs) relying on hidden trigger patterns inserted by hackers. We propose a training-free attack approach which is different from previous work, in which trojaned behaviors are injected by retraining model on a poisoned dataset. The proposed TrojanNet has several nice properties including (1) it activates by tiny trigger patterns and keeps silent for other signals, (2) it is model-agnostic and could be injected into most DNNs, dramatically expanding its attack scenarios, and (3) the training-free mechanism saves massive training efforts compared to conventional trojan attack methods.
  arXiv  Detail & Related papers  (2020-06-15T04:58:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.