Skip to content

Commit

Permalink
move seminar:5 to past
Browse files Browse the repository at this point in the history
  • Loading branch information
@DaoudiNadia
DaoudiNadia committed Dec 5, 2023
1 parent 7851471 commit e91748d
Showing 1 changed file with 36 additions and 27 deletions.
63 changes: 36 additions & 27 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -173,31 +173,7 @@ <h2>Upcoming Seminars<h2>
</div>

<div class="event-frame">


<div class="event">
<div class="presenter-details">
<img src="img/benjamin.jpg">
<h5> Benjamin Steenhoek </h5>
<p> Iowa State University </p>
</div>
<div class="event-info">
<h3>Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection</h3>
<p> Deep learning-based vulnerability detection has shown great performance and, in some studies, outperformed static analysis tools. However, the highest-performing
approaches use token-based transformer models, which are not the most efficient to capture code semantics required for vulnerability detection. In this paper, we propose
to combine such causal-based vulnerability detection algorithms with deep learning, aiming to achieve more efficient and effective vulnerability detection. Specifically,
we designed DeepDFA, a dataflow analysis-inspired graph learning framework and an embedding technique that enables graph learning to simulate dataflow computation. We show
that DeepDFA is both performant and efficient. DeepDFA outperformed all non-transformer baselines. It was trained in 9 minutes, 75x faster than the highest-performing baseline
model. When using only 50+ vulnerable and several hundreds of total examples as training data, the model retained the same performance as 100% of the dataset. DeepDFA also
generalized to real-world vulnerabilities in DbgBench; it detected 8.7 out of 17 vulnerabilities on average across folds and was able to distinguish between patched and buggy versions.
By combining DeepDFA with a large language model, we surpassed the state-of-the-art vulnerability detection performance on the Big-Vul dataset
with 96.46 F1 score, 97.82 precision, and 95.14 recall. </p>

<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black"><strong>Monday, December 4, 2023 at 3:00 PM CET</strong></span></p>

</div>
</div>



<div class="event">
<div class="presenter-details">
Expand All @@ -217,7 +193,7 @@ <h3>Robust Learning of Deep Predictive Models from Noisy and Imbalanced Software
and Software Defect Prediction. Evaluation results show that RobustTrainer effectively tackles the mislabelling and class imbalance issues and produces significantly better
deep predictive models compared to the other six comparison approaches. </p>

<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black"><strong>Monday, December 18, 2023 at 10:30 PM CET</strong></span></p>
<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black"><strong>Monday, December 18, 2023 at 10:30 AM CET</strong></span></p>

</div>
</div>
Expand All @@ -243,6 +219,39 @@ <h2>Past Seminars<h2>
<ul class="speech-list">


<li>
<div class="speech-header">
<b>Dataflow Analysis-Inspired DL for Efficient Vulnerability Detection</b>, Monday, December 4, 2023, by <b>Benjamin Steenhoek</b> from <b>ISU</b>

</div>

<div class="details">
<div class="event">
<div class="presenter-details">
<img src="img/benjamin.jpg">
<h5> Benjamin Steenhoek</h5>
<p> Iowa State University </p>
</div>
<div class="event-info">
<h3>Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection</h3>
<p> Deep learning-based vulnerability detection has shown great performance and, in some studies, outperformed static analysis tools. However, the highest-performing
approaches use token-based transformer models, which are not the most efficient to capture code semantics required for vulnerability detection. In this paper, we propose
to combine such causal-based vulnerability detection algorithms with deep learning, aiming to achieve more efficient and effective vulnerability detection. Specifically,
we designed DeepDFA, a dataflow analysis-inspired graph learning framework and an embedding technique that enables graph learning to simulate dataflow computation. We show
that DeepDFA is both performant and efficient. DeepDFA outperformed all non-transformer baselines. It was trained in 9 minutes, 75x faster than the highest-performing baseline
model. When using only 50+ vulnerable and several hundreds of total examples as training data, the model retained the same performance as 100% of the dataset. DeepDFA also
generalized to real-world vulnerabilities in DbgBench; it detected 8.7 out of 17 vulnerabilities on average across folds and was able to distinguish between patched and buggy versions.
By combining DeepDFA with a large language model, we surpassed the state-of-the-art vulnerability detection performance on the Big-Vul dataset
with 96.46 F1 score, 97.82 precision, and 95.14 recall. </p>

<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black">Monday, December 4, 2023 at 3:00 PM CET</span></p>

</div>
</div>
</div>
</li>



<li>
<div class="speech-header">
Expand All @@ -269,7 +278,7 @@ <h3>Towards Understanding Fairness and its Composition in Ensemble Machine Learn
ensembles can be designed to be fairer without using mitigation techniques. We also identify the interplay between fairness composition and data characteristics to guide fair
ensemble design.</p>

<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black"><strong>Monday, November 20, 2023 at 4:00 PM CET</strong></span></p>
<p><b><span class="black-underligned">Presentation Date:</span></b> <span class="black">Monday, November 20, 2023 at 4:00 PM CET</span></p>

</div>
</div>
Expand Down

0 comments on commit e91748d

Please sign in to comment.