Advances in adversarial attacks and defenses in computer vision: A survey
Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …
ability to accurately solve complex problems is employed in vision research to learn deep …
Backdoor learning: A survey
Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …
that the attacked models perform well on benign samples, whereas their predictions will be …
Plundervolt: Software-based fault injection attacks against Intel SGX
Dynamic frequency and voltage scaling features have been introduced to manage ever-
growing heat and power consumption in modern processors. Design restrictions ensure …
growing heat and power consumption in modern processors. Design restrictions ensure …
RIDL: Rogue in-flight data load
We present Rogue In-flight Data Load (RIDL), a new class of speculative unprivileged and
constrained attacks to leak arbitrary data across address spaces and privilege boundaries …
constrained attacks to leak arbitrary data across address spaces and privilege boundaries …
Electrical-level attacks on CPUs, FPGAs, and GPUs: Survey and implications in the heterogeneous era
Given the need for efficient high-performance computing, computer architectures combining
central processing units (CPUs), graphics processing units (GPUs), and field-programmable …
central processing units (CPUs), graphics processing units (GPUs), and field-programmable …
Threat of adversarial attacks on deep learning in computer vision: A survey
Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …
computer vision, it has become the workhorse for applications ranging from self-driving cars …
A modern primer on processing in memory
Modern computing systems are overwhelmingly designed to move data to computation. This
design choice goes directly against at least three key trends in computing that cause …
design choice goes directly against at least three key trends in computing that cause …
TRRespass: Exploiting the many sides of target row refresh
After a plethora of high-profile RowHammer attacks, CPU and DRAM vendors scrambled to
deliver what was meant to be the definitive hardware solution against the RowHammer …
deliver what was meant to be the definitive hardware solution against the RowHammer …
Tbt: Targeted neural network attack with bit trojan
Abstract Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the
deployment of these models become widespread in many intelligence-based applications …
deployment of these models become widespread in many intelligence-based applications …
Processing data where it makes sense: Enabling in-memory computation
Today's systems are overwhelmingly designed to move data to computation. This design
choice goes directly against at least three key trends in systems that cause performance …
choice goes directly against at least three key trends in systems that cause performance …