NDLI: Machine Learning under Attack: Vulnerability Exploitation and Security Measures

Please wait, while we are loading the content...

Machine Learning under Attack: Vulnerability Exploitation and Security Measures

Bringing Multimedia Security from the Research Lab to the Forensic Lab

A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer

Dynamic Privacy-Preserving Genomic Susceptibility Testing

Provable Secure Universal Steganography of Optimal Rate: Provably Secure Steganography does not Necessarily Imply One-Way Functions

A Survey and Taxonomy Aimed at the Detection and Measurement of Covert Channels

Information Hiding in the RSA Modulus

Enhanced Collusion Resistance for Segment-wise Recombined Fingerprinting in P2P Distribution Systems: [Extended Abstract]

Forensics of High Quality and Nearly Identical JPEG Image Recompression

Group Testing for Identification with Privacy

Rethinking Optimal Embedding

A Novel Embedding Distortion for Motion Vector-Based Steganography Considering Motion Characteristic, Local Optimality and Statistical Distribution

Secure Image Display through Visual Cryptography: Exploiting Temporal Responsibilities of the Human Eye

Study of a Verifiable Biometric Matching

A Higher Order Analysis of the Joint Capacity of Digital Fingerprinting Codes against the Interleaving Attack

Differentially Private Matrix Factorization using Sketching Techniques

Ensemble of CNNs for Steganalysis: An Empirical Study

Constructing Near-optimal Double-layered Syndrome-Trellis Codes for Spatial Steganography

Image Segmentation Based Visual Security Evaluation

Privacy Protection for JPEG Content on Image-Sharing Platforms

Efficient HS based Reversible Data Hiding Using Multi-feature Complexity Measure and Optimized Histogram

Secure and Verifiable Outsourcing of Nonnegative Matrix Factorization (NMF)

Color Image Steganalysis Based On Steerable Gaussian Filters Bank

Boosting Steganalysis with Explicit Feature Maps

PPE-Based Reversible Data Hiding

A Novel CDMA Based High Performance Reversible Data Hiding Scheme

Practical and Scalable Sharing of Encrypted Data in Cloud Storage with Key Aggregation

Machine Learning under Attack: Vulnerability Exploitation and Security Measures

Content Provider	ACM Digital Library
Author	Biggio, Battista
Abstract	Learning to discriminate between secure and hostile patterns is a crucial problem for species to survive in nature. Mimetism and camouflage are well-known examples of evolving weapons and defenses in the arms race between predators and preys. It is thus clear that all of the information acquired by our senses should not be considered necessarily secure or reliable. In machine learning and pattern recognition systems, however, we have started investigating these issues only recently. This phenomenon has been especially observed in the context of adversarial settings like malware detection and spam filtering, in which data can be purposely manipulated by humans to undermine the outcome of an automatic analysis. As current pattern recognition methods are not natively designed to deal with the intrinsic, adversarial nature of these problems, they exhibit specific vulnerabilities that an attacker may exploit either to mislead learning or to evade detection. Identifying these vulnerabilities and analyzing the impact of the corresponding attacks on learning algorithms has thus been one of the main open issues in the novel research field of adversarial machine learning, along with the design of more secure learning algorithms. In the first part of this talk, I introduce a general framework that encompasses and unifies previous work in the field, allowing one to systematically evaluate classifier security against different, potential attacks. As an example of application of this framework, in the second part of the talk, I discuss evasion attacks, where malicious samples are manipulated at test time to evade detection. I then show how carefully-designed poisoning attacks can mislead some learning algorithms by manipulating only a small fraction of their training data. In addition, I discuss some defense mechanisms against both attacks in the context of real-world applications, including biometric identity recognition and computer security. Finally, I briefly discuss our ongoing work on attacks against clustering algorithms, and sketch some promising future research directions.
Starting Page	1
Ending Page	2
Page Count	2
File Format	PDF
ISBN	9781450342902
DOI	10.1145/2909827.2930784
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-06-20
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Evasion attacks Poisoning attacks Adversarial machine learning Secure pattern recognition
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

On learning and recognition of secure patterns

Secure Kernel Machines against Evasion Attacks

Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks

Attack Tree Analysis for Adversarial Evasion Attacks

ML Attack Models: Adversarial Attacks and Data Poisoning Attacks

Understanding and Diagnosing Vulnerability under Adversarial Attacks

AppCon: Mitigating Evasion Attacks to ML Cyber Detectors

Adversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attacks

Hardness of evasion of multiple classifier system with non-linear classifiers

Machine Learning under Attack: Vulnerability Exploitation and Security Measures

Similar Documents

On learning and recognition of secure patterns

Secure Kernel Machines against Evasion Attacks

Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks

Attack Tree Analysis for Adversarial Evasion Attacks

ML Attack Models: Adversarial Attacks and Data Poisoning Attacks

Understanding and Diagnosing Vulnerability under Adversarial Attacks

AppCon: Mitigating Evasion Attacks to ML Cyber Detectors

Adversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attacks

Hardness of evasion of multiple classifier system with non-linear classifiers

Machine Learning under Attack: Vulnerability Exploitation and Security Measures