Triggerless Backdoor Attack Against Deep Neural Networks

guest · Nov 2, 2020

‘Triggerless’ backdoors can infect machine learning models without leaving a trace – research
New attack bypasses most of the current defense methods being used to protect deep learning systems
November 2, 2020
https://portswigger.net/daily-swig/...rning-models-without-leaving-a-trace-research

Malicious actors can cause artificial intelligence systems to act erratically without using visible ‘triggers’, researchers at the Germany-based CISPA Helmholtz Center for Information Security have found.

In a paper submitted to the ICLR 2021 conference, the researchers show a proof of concept for so-called ‘triggerless backdoors’ in deep learning systems – a new type of attack that bypasses most of the defense methods that are currently being deployed.
Click to expand...

In the triggerless backdoor scheme, attackers manipulate the deep learning model to activate the malicious behavior when specific neurons are dropped.
Probabilistic attack
The benefit of the triggerless backdoor is that the attacker no longer needs visible triggers to activate the malicious behavior – but it does come with some tradeoffs.

This is nonetheless the first attack of its kind and can provide new directions for research on backdoor attacks and defense methods.

“We plan to continue working on exploring the privacy and security risks of machine learning and how to develop more robust machine learning models,” Salem says.
Click to expand...

Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks

Abstract: Backdoor attack against deep neural networks is currently being profoundly investigated due to its severe security consequences. Current state-of-the-art backdoor attacks require the adversary to modify the input, usually by adding a trigger to it, for the target model to activate the backdoor.

This triggerless feature of our attack makes it practical in the physical world. Extensive experiments show that our triggerless backdoor attack achieves a perfect attack success rate with a negligible damage to the model's utility.
Click to expand...

Log in or Sign up

Triggerless Backdoor Attack Against Deep Neural Networks

guest Guest

Log in or Sign up

Triggerless Backdoor Attack Against Deep Neural Networks

guest Guest

Useful Searches