Tag: ARTICLE

This article concludes our four-part series on the basic differences between traditional IT security and blockchain security. Previous articles discussed the security differences critical...

In recent years, the rise of artificial intelligence (AI) has revolutionized many sectors, bringing about significant advancements in various fields. However, one area where AI has presented a dual-edged sword is in information operations, specifically in the propagation of disinformation. The advent of generative AI, particularly with sophisticated models capable of creating highly realistic text, images, audio, and video, has exponentially increased the risk of deepfakes and other forms of disinformation.

GAN Poisoning is a unique form of adversarial attack aimed at manipulating Generative Adversarial Networks (GANs) during their training phase; unlike traditional cybersecurity threats like data poisoning or adversarial input attacks, which either corrupt training data or trick already-trained models, GAN Poisoning focuses on altering the GAN's generative capability to produce deceptive or harmful outputs. The objective is not merely unauthorized access but the generation of misleading or damaging information.

Emergent behaviours in AI have left both researchers and practitioners scratching their heads. These are the unexpected quirks and functionalities that pop up in complex AI systems, not because they were explicitly trained to exhibit them, but due to the intricate interplay of the system's complexity, the sheer volume of data it sifts through, and its interactions with other systems or variables. It's like giving a child a toy and watching them use it to build a skyscrapper. While scientists hoped that scaling up AI models would enhance their performance on familiar tasks, they were taken aback when these models started acing a number of unfamiliar tasks.

I’m skeptical of ‘futurists’. Work closely enough with the development of technology solutions and you’ll know that the only certain thing about the future...

This article is the third in a four-part series exploring the differences between traditional IT security and blockchain security.  Check out the first two...

This article is the second in a four-part series discussing the differences between traditional IT security / cybersecurity and blockchain security.  Check out the...

Data masking, also known as data obfuscation or data anonymization, serves as a crucial technique for ensuring data confidentiality and integrity, particularly in non-production environments like development, testing, and analytics. It operates by replacing actual sensitive data with a sanitized version, rendering the data ineffective for malicious exploitation while retaining its functional utility for testing or analysis.

Label-flipping attacks refer to a class of adversarial attacks that specifically target the labeled data used to train supervised machine learning models. In a typical label-flipping attack, the attacker changes the labels associated with the training data points, essentially turning "cats" into "dogs" or benign network packets into malicious ones, thereby aiming to train the model on incorrect or misleading associations. Unlike traditional adversarial attacks that often focus on manipulating the input features or creating adversarial samples to deceive an already trained model, label-flipping attacks strike at the root of the learning process itself, compromising the integrity of the training data.

Recent events like the FTX meltdown have sparked interest and conversations about how the incident could have been prevented.  In the case of FTX,...

Blockchain is a rapidly-evolving technology with a great deal of interest and investment. Decentralized Finance (DeFi), in particular, has a great deal of money...

The most comprehensive ranked list of the biggest crypto hacks in history (Up until November 1, 2022. I suspect a larger one is just...

Backdoor attacks in the context of Machine Learning (ML) refer to the deliberate manipulation of a model's training data or its algorithmic logic to implant a hidden vulnerability, often referred to as a "trigger." Unlike typical vulnerabilities that are discovered post-deployment, backdoor attacks are often premeditated and planted during the model's development phase. Once deployed, the compromised ML model appears to function normally for standard inputs. However, when the model encounters a specific input pattern corresponding to the embedded trigger, it produces an output that is intentionally skewed or altered, thereby fulfilling the attacker's agenda.

$566M worth of BNB was stolen from Binance’s cross-chain bridge BSC Token Hub, but how they responded to the hack will be the most...

Understanding how flash loans and governance work in DeFi to demystify the Beanstalk Farms Hack The only way to understand how the Beanstalk Farms decentralized...