The code mimics the mechanisms by which the immune system learns to identify antigens, instead learning to characterize the dubious inputs to the machine learning algorithm.
Image credit: Ren Wang
The adaptive immune system serves as a template for defending neural nets from confusion-sowing attacks
If a sticker on a banana can make it show up as a toaster, how might strategic vandalism warp how an autonomous vehicle perceives a stop sign? Now, an immune-inspired defense system for neural networks can ward off such attacks, designed by engineers, biologists and mathematicians at the University of Michigan.
Deep neural networks are a subset of machine learning algorithms used for a wide variety of classification problems. These include image identification and machine vision (used by autonomous vehicles and other robots), natural language processing, language translation and fraud detection. However, it is possible for a nefarious person or group to adjust the input slightly and send the algorithm down the wrong train of thought, so to speak. To protect algorithms against such attacks, the Michigan team developed the Robust Adversarial Immune-inspired Learning System.
“RAILS represents the very first approach to adversarial learning that is modeled after the adaptive immune system, which operates differently than the innate immune system,” said Alfred Hero, the John H. Holland Distinguished University Professor, who co-led the work published in IEEE Access.
While the innate immune system mounts a general attack on pathogens, the mammalian adaptive immune system can generate new cells designed to defend against specific pathogens. It turns out that deep neural networks, already inspired by the brain’s system of information processing, can take advantage of this biological process, too.
“The immune system is built for surprises,” said Indika Rajapakse, associate professor of computational medicine and bioinformatics and co-leader of the study. “It has an amazing design and will always find a solution.”
RAILS works by mimicking the natural defenses of the immune system to identify and ultimately take care of suspicious inputs to the neural network. To begin developing it, the biological team studied how the adaptive immune systems of mice responded to an antigen. The experiment used the tissues of genetically modified mice that express fluorescent markers on their B cells.
The team created a model of the immune system by culturing cells from the spleen together with those of bone marrow, representing a headquarters and garrison of the immune system. This system enabled the biological team to track the development of B cells, which starts as a trial-and-error approach to designing a receptor that binds to the antigen. Once the B-cells converge on a solution, they produce both plasma B cells for capturing any antigens present and memory B cells in preparation for the next attack.
Stephen Lindsly, a doctoral student in bioinformatics at the time, performed data analysis on the information generated in Rajapakse’s lab and acted as a translator between the biologists and engineers. Hero’s team then modeled that biological process on computers, blending biological mechanisms into the code. They tested the RAILS defenses with adversarial inputs. Then they compared the learning curve of the B cells learning to attack antigens with the algorithm learning to exclude those bad inputs.
“We weren’t sure that we had really captured the biological process until we compared the learning curves of RAILS to those extracted from the experiments,” Hero said. “They were exactly the same.”
Not only was it an effective biomimic, RAILS outperformed two of the most common machine learning processes used to combat adversarial attacks: Robust Deep k-Nearest Neighbor and convolutional neural networks.
“One very promising part of this work is that our general framework can defend against different types of attacks,” said Ren Wang, a research fellow in electrical and computer engineering, who was primarily responsible for the development and implementation of the software.
The researchers used image identification as the test case, evaluating RAILS against eight types of adversarial attacks in several datasets. It showed improvement in all cases, including protection against the most damaging type of adversarial attack—known as a Projected Gradient Descent attack. In addition, RAILS improved the overall accuracy. For instance, it helped correctly identify an image of a chicken and an ostrich, widely perceived as a cat and a horse, as two birds.
“This is an amazing example of using mathematics to understand this beautiful dynamical system,” Rajapakse said. “We may be able to take what we learned from RAILS and help reprogram the immune system to work more quickly.”
Future efforts from Hero’s team will focus on reducing the response time from milliseconds to microseconds.
Original Article: Immune to hacks: Inoculating deep neural networks to thwart attacks
More from: University of Michigan
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Robust Adversarial Immune-inspired Learning System
- The Immune System in the Elderly: A Fair Fight Against Diseases?
The link between these diseases is immunity, and loss of immune functions may explain the age-associated incidence of such diseases by reduced immunosurveillance, polyfunctionality or regulation.
- The Immune System in the Elderly: A Fair Fight Against Diseases?
Aging Health. 2013;9(1):35-47. Loss of immune function – that is, immunosenescence – is considered an important determinant of health. Both adaptive and innate immunity are affected with age.
- Study rethinks immune system strategies to boost vaccine effectiveness
A recent Cell journal review explores key immunological assumptions to enhance our understanding of vaccine design, autoimmune responses, and immune system pathology, aiming to refine intervention ...
- What’s Going On in This Picture?
By The Learning Network Look closely at this image, stripped of its caption, and join the moderated conversation about what you and other students see. By The Learning Network Want to use ...
- Immune System News
May 3, 2024 — Scientists have discovered how glioblastoma evades the immune system by inducing pro-tumor macrophages via a glucose based epigenetic ... May 2, 2024 — A new study has revealed ...
Go deeper with Google Headlines on:
Robust Adversarial Immune-inspired Learning System
[google_news title=”” keyword=”Robust Adversarial Immune-inspired Learning System” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Deep neural networks
- New Study Redefines Human Sound Localization
Researchers challenged a longstanding theory from the 1940s about how humans locate sounds, a discovery with profound implications for hearing technology.
- AI Deep Learning Improves Brain-Computer Interface Performance
AI deep learning powers a brain-computer interface that enables humans to continuously control a cursor using thoughts.
- ATR Network: Decentralized private data multimodal supercomputing network
On the basis of protecting data and privacy security, ATR Network uses neural network, deep learning and other technologies to deeply analyze heterogeneous data, extract useful data vectors, and ...
- Neuroscientists Reveal 'Neural Compass' That Stops You From Getting Lost
The discovery offers new insights for conditions like Parkinson's disease and Alzheimer's, in which navigation and orientation are often impaired.
- New Deep Instinct AI assistant bridges the gap in malware analysis
Threat protection-focused startup Deep Instinct Ltd. today announced the launch of DIANNA — short for Deep Instinct’s Artificial Neural Network Assistant, a new generative artificial intelligence ...
Go deeper with Google Headlines on:
Deep neural networks
[google_news title=”” keyword=”deep neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]