Technology

‘AI defense development may gain insight from biological immune systems’: DARPA

“Novel adversarial AI defense development may gain insight and inspiration from biological systems, such as the immune system and its interactions with bacteria and viruses,” according to a DARPA proposal.

Read More: Nature is intelligent: Pentagon looks to insects for AI biomimicry design

The research funding arm of the Pentagon is worried that “adversaries” could turn AI against its programmers by “poisoning” it into doing the biddings of those it wasn’t meant to serve.

With “poisoning attacks,” attackers deliberately influence the training data to manipulate the results of a predictive model, according to IEEE.

Read More: DARPA launches AI chemistry program to develop new molecules for military use

If we look towards natural models for an analogy, it would be like how a virus could manipulate the immune system of the host so it would attack itself, or how bacteria could change the host environment so it could grow stronger and spread.

“The lack of a comprehensive theoretical understanding of ML vulnerabilities leaves significant exploitable blind spots”

The Defense Advanced Research Projects Agency (DARPA) will hold a Proposers Day on February 6, 2019 for a program aimed at developing a new generation of defenses against adversarial deception attacks on machine learning (ML) models, such as poisoning attacks and inference attacks — “where malicious users infer sensitive information from complex databases at a high level,” thus endangering the integrity of an entire database,” according to Techopedia.

DARPA’s Guaranteeing AI Robustness against Deception (GARD) program will seek game-changing research ideas to
develop theory, defenses, and testbeds leading to robust, deception-resistant ML models and algorithms.

GARD seeks to push the state-of-the-art in ML defenses beyond classification by defending via detection, location, and prediction, and beyond the standard modality of digital images by developing defenses against physical world attacks in a variety of pertinent modalities, such as video and audio.

GARD has three objectives:

  1. Develop theoretical foundations for defensible ML. These foundations will include metrics for measuring ML vulnerability and identifying ML properties that enhance system robustness
  2. Create, and empirically test, principled defense algorithms in diverse settings
  3. Construct a scenario-based evaluation framework to characterize defenses under multiple objectives and threat models such as the physical world and multimodal settings.

“The field now appears increasingly pessimistic, sensing that developing effective ML defenses may prove significantly more difficult than designing new attacks”

According to DARPA, “the growing sophistication and ubiquity of ML components in advanced systems dramatically increases capabilities, but as a byproduct, increases opportunities for new, potentially unidentified vulnerabilities.

“The acceleration in ML attack capabilities has promoted an arms race: as defenses are developed to address new attack strategies and vulnerabilities, improved attack methodologies capable of bypassing the defense algorithms are created.

Read More: DARPA wants to make AI a ‘collaborative partner’ for national defense

“The field now appears increasingly pessimistic, sensing that developing effective ML defenses may prove significantly more difficult than designing new attacks, leaving advanced systems vulnerable and exposed.

“Further, the lack of a comprehensive theoretical understanding of ML vulnerabilities in the ‘Adversarial Examples’ field leaves significant exploitable blind spots in advanced systems and limits efforts to develop effective defenses.”

Tim Hinchliffe

The Sociable editor Tim Hinchliffe covers tech and society, with perspectives on public and private policies proposed by governments, unelected globalists, think tanks, big tech companies, defense departments, and intelligence agencies. Previously, Tim was a reporter for the Ghanaian Chronicle in West Africa and an editor at Colombia Reports in South America. These days, he is only responsible for articles he writes and publishes in his own name. tim@sociable.co

View Comments

Recent Posts

MWC 2025 Barcelona was the ultimate experiential marketing dream

Mobile World Congress (MWC) in Barcelona is the biggest annual event in the mobile technology…

13 hours ago

GAN, Tec de Monterrey partnership highlights cross-border startup ecosystem building in Latin America amid trade dispute

Despite recent tensions between the United States government and Latin American countries over migration and…

5 days ago

This founder started out with US $5K to his name. Now, he owns a multi-million-dollar global business

Meet Nitin Seth, the Co-Founder and CEO of Screen Magic (SMS Magic), a messaging leader…

5 days ago

Building smarter: AI, the ultimate tool transforming an old-age industry

In this Brains Byte Back, we sit down with Hari Vasudevan, founder and CEO of…

5 days ago

When AI Goes Rogue: 8 Lessons from Implementing LLMs in the Healthcare Industry that Could Save the Future

By Santosh Shevade, Principal Data Consultant at Gramener – A Straive company All pharmaceutical companies…

6 days ago

Digital Public Infrastructure will enable public, private entities to control your access to essential goods, services & mobility

Digital Public Infrastructure is a top-down agenda coming from unelected globalists, bureaucrats, and their partners…

2 weeks ago