Machine Learning Security Evasion Competition 2020 Invites Researchers to Defend and Attack

Machine learning ML is an increasingly valuable tool in cyber security as adversaries continually evolve their tactics and techniques to evade detection. As machine learning has advanced and sophisticated ML models have been developed to assist security professionals in protecting the cloud,...

Facebook Announces Messenger Security Features that Don't Compromise Privacy

Note that this is "announced," so we don't know when it's actually going to be implemented. Facebook today announced new features for Messenger that will alert you when messages appear to come from financial scammers or potential child abusers, displaying warnings in the Messenger app that provid...

Long Tail Analysis: A New Hope in the Cybercrime Battle

Our hyper-connected world and its ever-faster network speeds have resulted in mountains of diverse data that needs to be processed. It has also resulted in an ever-expanding attack surface, requiring cybersecurity solutions to scale like never before. These days, scale is about more than traffic...

Microsoft researchers work with Intel Labs to explore new deep learning approaches for malware classification

The opportunities for innovative approaches to threat detection through deep learning, a category of algorithms within the larger framework of machine learning, are vast. Microsoft Threat Protection today uses multiple deep learning-based classifiers that detect advanced threats, for example,...

Fooling NLP Systems Through Word Swapping

MIT researchers have built a system that fools natural-language processing systems by swapping words with synonyms: The software, developed by a team at MIT, looks for the words in a sentence that are most important to an NLP classifier and replaces them with a synonym that a human would find...

Deepfakes and AI: Fighting Cybersecurity Fire with Fire

Today, the most successful and damaging cyberattacks are executed by highly professional criminal networks rather than “lone-wolf” hackers. These criminal organizations have also become highly adept at leveraging artificial intelligence AI and machine learning ML tools, making it extremely hard f...

Vulnerability Finding Using Machine Learning

Microsoft is training a machine-learning system to find software bugs: At Microsoft, 47,000 developers generate nearly 30 thousand bugs a month. These items get stored across over 100 AzureDevOps and GitHub repositories. To better label and prioritize bugs at that scale, we couldn't just apply mo...

Secure the software development lifecycle with machine learning

Every day, software developers stare down a long list of features and bugs that need to be addressed. Security professionals try to help by using automated tools to prioritize security bugs, but too often, engineers waste time on false positives or miss a critical security vulnerability that has...

CVE-2019-20634

An issue was discovered in Proofpoint Email Protection through 2019-09-08. By collecting scores from Proofpoint email headers, it is possible to build a copy-cat Machine Learning Classification model and extract insights from this model. The insights gathered allow an attacker to craft emails tha...

CVE-2019-20634

An issue was discovered in Proofpoint Email Protection through 2019-09-08. By collecting scores from Proofpoint email headers, it is possible to build a copy-cat Machine Learning Classification model and extract insights from this model. The insights gathered allow an attacker to craft emails tha...

Code injection

An issue was discovered in Proofpoint Email Protection through 2019-09-08. By collecting scores from Proofpoint email headers, it is possible to build a copy-cat Machine Learning Classification model and extract insights from this model. The insights gathered allow an attacker to craft emails tha...

CVE-2019-20634

CVE-2019-20634 concerns Proofpoint Email Protection (through 2019-09-08). The issue enables an attacker to collect scores from Proofpoint email headers to build a copy-cat machine learning classification model and extract insights. Using those insights, the attacker can craft emails that receive ...

PT-2020-10610 · Proofpoint · Proofpoint Email Protection

Name of the Vulnerable Software and Affected Versions: Proofpoint Email Protection versions prior to 2019-09-08 Description: An issue was discovered in Proofpoint Email Protection. By collecting scores from Proofpoint email headers, it is possible to build a copy-cat Machine Learning Classificati...

Tokyo Olympics Postponed, But 5G Security Lessons Shine

The 2020 Summer Olympics in Tokyo were officially postponed this week amid the ongoing, pandemic spread of the coronavirus that causes COVID-19. The Games will be moved to 2021, but in the meantime, technological innovation around the event will continue. More specifically, postponed or not, the...

Machine learning classifiers trained via gradient descent are vulnerable to arbitrary misclassification attack

Overview Machine learning models trained using gradient descent can be forced to make arbitrary misclassifications by an attacker that can influence the items to be classified. The impact of a misclassification varies widely depending on the ML model's purpose and of what systems it is a part...

Security Bulletin: A security vulnerability has been identified in TensorFlow shipped with PowerAI.

Summary Vulnerability CVE-2020-5215 found in TensorFlow package. Vulnerability Details CVEID: CVE-2020-5215 DESCRIPTION: Tensorflow is vulnerable to a denial of service, caused by a flaw when converting a string from Python to a tf.float16 value. By sending a specially-crafted string, a remote...

Security Bulletin: A security vulnerability has been identified in SQLite shipped with PowerAI.

Summary Vulnerability CVE-2019-19317 found in SQLite package. Vulnerability Details CVEID: CVE-2019-19317 DESCRIPTION: SQLite is vulnerable to a denial of service, caused by an error in lookupName in resolve.c. By providing specially crafted input, a remote attacker could exploit this vulnerabili...

Security Bulletin: A security vulnerability has been identified in SQLite shipped with PowerAI.

Summary Multiple vulnerabilities CVE-2019-19242 and CVE-2019-19244 found in SQLite package. Vulnerability Details CVEID: CVE-2019-19242 DESCRIPTION: An unspecified error with the mishandling of pExpr-y.pTab in the sqlite3ExprCodeTarget function in expr.c in SQLite has an unknown impact and attack...

New Research Paper: Prevalence and impact of low-entropy packing schemes in the malware ecosystem

Detection of malware is a constant battle between the technologies designed to detect and prevent malware and the authors creating them. One common technique adversaries leverage is packing binaries. Packing an executable is similar to applying compression or encryption and can inhibit the abilit...

RSAC 2020: Lack of Machine Learning Laws Open Doors To Attacks

SAN FRANCISCO – As companies quickly adopt machine learning systems, cybercriminals are close behind scheming to compromise them. That worries legal experts who say a lack of laws swing open the door for bad guys to attack systems. During a panel session at RSA Conference 2020 this week, Cristin...