SentiNet: Detecting Physical Attacks Against Deep Learning Systems

By Edward Chou, Florian Tramèr, Giancarlo Pellegrino, Dan Boneh. 2018

111 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

Citations in the corpus

You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion (2020, background): “tently change the model’s output [36, 65], (2) use anomalies in the model’s internal behavior to identify poisoned inputs in the training data [12, 15, 59], or (3) prevent rare features in the training data from influencing the model [19, 28, 35].”
DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks (2019, background): “Existing papers [Chen et al., 2018; Chou et al., 2018] mainly focused on identifying whether the input contains the trigger assuming the queried model has been infected (i.e., ‘sanity check of the input’).”
STRIP: a defence against trojan attacks on deep neural networks (2019, methodology): “Notably, the triggers used in this paper are those that have been used to perform trojan attacks in [8], [16] and also used to evaluate countermeasures against trojan attacks in [11], [17].”
NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations (2019, background): “SentiNet (Chou et al. 2018) is an attack agnostic framework detecting trojan backdoor attacks on DNN.”
Security and Privacy Challenges of Large Language Models: A Survey (2024, unknown): “…in LMs, like, TROJANLM [98], one possible defense technique is to adopt existing techniques from other domains such as images, e.g., detecting trigger-embedded inputs at inference time [155], [168], and finding suspicious LMs and retrieving triggers during the model evaluation phase [169], [170].”
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection (2019, methodology): “Other attempts analyze a target model’s behavior towards a synthesized image created by blending those with different labels [10], or images with and without triggers [9], to determine the presence of a backdoor.”
Februus: Input Purification Defence Against Trojan Attacks on Deep Neural Network Systems (2019, background): “Identical to the approach of recent papers [9, 10, 24], we focus on input-agnostic attacks while the trigger will misclassify any inputs to a targeted class regardless input sources (illustrated in Figure 2).”
ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation (2019, unknown): “Some [18, 40, 57, 63] detect whether an input is an adversarial example and could be potentially used for detecting pixel space trojan triggers.”
Blind Backdoors in Deep Learning Models (2020, methodology): “SentiNet [12] identifies which regions of an image are important for the model’s classification of that image, under the assumption that a backdoored model always “focuses” on the backdoor feature.”
TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems (2019, background): “propose SentiNet [9], a different technical approach to detect the presence of the trigger in a target input sample.”
Detecting AI Trojans Using Meta Neural Analysis (2019, methodology): “These approaches can be categorized into input-level detection [20], [15], [38], model-level detection [51] and dataset-level detection [12].”
AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning (2018, background): “, black-box attacks [19] or physicallyrealizable attacks [21].”