Author name cluster

Seijoon Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

TMLR Journal 2026 Journal Article

Hessian-aware Training for Enhancing DNN Resilience to Bitwise Corruptions in Their Parameters

Tahmid Hasan Pranto
Seijoon Kim
Lizhong Chen
Sanghyun Hong

Deep neural networks are not resilient to parameter corruptions: even a single-bitwise error in their parameters in memory can cause an accuracy drop of over 10%, and in the worst-cases, up to 99%. This susceptibility poses great challenges in deploying models on computing platforms, where adversaries can induce random/targeted bit-flips, e.g., through software-induced fault attacks like Rowhammer. Most prior work addresses this issue with hardware or system-level approaches, such as integrating additional hardware components to verify a model’s integrity at inference. However, these methods have not been widely deployed as they require infrastructure or platform-wide modifications. In this paper, we propose a new approach to addressing this issue: training models to be more resilient to bitwise corruptions to their parameters. Our approach, Hessian-aware training, promotes models to learn flatter loss surfaces. We show that existing training methods designed to improve generalization (e.g., through sharpness-aware minimization) do not enhance resilience to parameter corruptions. In contrast, models trained with our method demonstrate improved resilience to parameter corruptions, particularly with a 20–50% reduction in the number of bits whose individual flipping leads to a 90–100% accuracy drop. We also characterize the factors that may influence this increased resilience. Moreover, we show the synergy between ours and existing hardware and system-level defenses.

PDF Details

AAAI Conference 2020 Conference Paper

Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection

Seijoon Kim
Seongsik Park
Byunggook Na
Sungroh Yoon

Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-generation of neural networks due to their event-driven and low-powered nature. SNNs, however, are difﬁcult to train, mainly owing to their complex dynamics of neurons and non-differentiable spike operations. Furthermore, their applications have been limited to relatively simple tasks such as image classiﬁcation. In this study, we investigate the performance degradation of SNNs in a more challenging regression problem (i. e. , object detection). Through our in-depth analysis, we introduce two novel methods: channel-wise normalization and signed neuron with imbalanced threshold, both of which provide fast and accurate information transmission for deep SNNs. Consequently, we present a ﬁrst spiked-based object detection model, called Spiking-YOLO. Our experiments show that Spiking-YOLO achieves remarkable results that are comparable (up to 98%) to those of Tiny YOLO on non-trivial datasets, PASCAL VOC and MS COCO. Furthermore, Spiking-YOLO on a neuromorphic chip consumes approximately 280 times less energy than Tiny YOLO and converges 2. 3 to 4 times faster than previous SNN conversion methods.

PDF Details

AAAI Conference 2018 Conference Paper

Quantized Memory-Augmented Neural Networks

Seongsik Park
Seijoon Kim
Seil Lee
Ho Bae
Sungroh Yoon

Memory-augmented neural networks (MANNs) refer to a class of neural network models equipped with external memory (such as neural Turing machines and memory networks). These neural networks outperform conventional recurrent neural networks (RNNs) in terms of learning long-term dependency, allowing them to solve intriguing AI tasks that would otherwise be hard to address. This paper concerns the problem of quantizing MANNs. Quantization is known to be effective when we deploy deep models on embedded systems with limited resources. Furthermore, quantization can substantially reduce the energy consumption of the inference procedure. These beneﬁts justify recent developments of quantized multilayer perceptrons, convolutional networks, and RNNs. However, no prior work has reported the successful quantization of MANNs. The in-depth analysis presented here reveals various challenges that do not appear in the quantization of the other networks. Without addressing them properly, quantized MANNs would normally suffer from excessive quantization error which leads to degraded performance. In this paper, we identify memory addressing (speciﬁcally, content-based addressing) as the main reason for the performance degradation and propose a robust quantization method for MANNs to address the challenge. In our experiments, we achieved a computation-energy gain of 22× with 8-bit ﬁxedpoint and binary quantization compared to the ﬂoating-point implementation. Measured on the bAbI dataset, the resulting model, named the quantized MANN (Q-MANN), improved the error rate by 46% and 30% with 8-bit ﬁxed-point and binary quantization, respectively, compared to the MANN quantized using conventional techniques.

PDF Details