Marius Manica

Cyber Incident Response Adobe


Having more than 7 years of experience in security, Marius has had the opportunity to see all of the branches of the industry – from state institutions to state-sponsored attacks, from private companies to privacy incidents, from law enforcement to security analyst to threat hunter and incident responder. Having had this level of exposure in such a short time has allowed him to learn faster and faster and keep up with the industry. Anyone that worked with him would describe Marius as a professional first and foremost. His dedication can be seen from his highly-focused work ethic and attention to details.

Project SCOUT. Deep Learning for malicious code detection

The number of client-side attack vectors has increased dramatically in the last decade. From exploiting browser vulnerabilities to miners or drive-by downloads, attackers commonly use Javascript code to achieve their goals. In the past, malicious code classification has been achieved using standard feature-engineering over static code analysis or dynamic code execution patterns.
We propose a new deep-learning inspired methodology for detecting malicious code, based on latent representations computed in an un-supervised manner. We explore three different methodologies for computing the latent representations in a deep encoder-decoder architecture: self-attention, global style tokens (GST) and “memory-based” representations.
The three strategies for computing latent representations capture different aspects of how the code is written: (a) the GST tokens capture specific attacker techniques like code that is obfuscated or encrypted or that does many string manipulations; (b) the memory-based method learns “code patterns” such as iterators, if/else statements, asserts etc. and (c) the multi-head attention method captures on-the-fly summarizations of code-segments that are hard to reconstruct (don’t follow standard patterns).
1. The self-attention model represents code as the concatenated values of all heads in a multi-head attention system;
2. The GST method computes a probability distribution (attention) over a fixed number of style tokens (embeddings) and the latent representation is obtained as the weighted sum over all the tokens;
3. Finally, the memory-based method is similar to GST, but it computes multiple probability distributions over different buckets of style-tokens.

The latent code representations are used as input for a multilayer perceptron that classifies a code segment as being malicious or not. Our initial experiments on previously unseen data show state-of-the art results in classifying both isolated code-sequences as well as entire JS files as being malicious or benign.

The same latent-representation extraction methodology can be used over multiple datasets, regardless of the programming language, to attend a wide-variety of code-related tasks or problems as: identifying vulnerable code, identifying bad practices, indexing code (finding similar code), copyright issues, etc.
This talk is co-presented with Tiberiu Boros, Computer Scientist at Adobe

Are you the next cyber security superstar?

If you are passionate about an information security topic or you have strong technical skills developing researches on your own, you should definitely Apply at Call for Papers. By submitting you will have the chance to showcase your work to +2000 attendees.

Other speakers joining this year

Razvan Bocu

Lecturer and Researcher Transilvania University of Brasov, Romania


Sebastian Avarvarei

Director for Security Advisory Services Wolters Kluwer


Senior Security Researcher 360 Security Technology

Ready for this year's presentations?

By registering you will unlock access to 60+ speakers and two full days with cyber security news & showcases from worldwide leaders.


Sponsors & Partners

They help us make this conference possible.


At Orange Business Services, we help our customers transform their industries, reimagine their services, create a positive impact and unleash the power of their data into an amazing and trusted resource.

With the dual expertise as a global operator coupled with the agility of an end-to-end integrator, Orange Business Services is a global network-native, digital services company. From connectivity, smart mobility services and the cloud to artificial intelligence (AI), analytics and cybersecurity, Orange Business Services helps businesses at every stage of their data management. Orange Business Services is represented in Romania by the business division of Orange Romania and helps large companies, SMEs and public authorities to transform their organizations through the use of technology and digital information.

Platinum Partners

Gold Partners

pentest tools defcamp

defcamp 2022 booking holdings

Silver Partners

siemens defcamp 2022

huawei defcamp 2022

Bronze Partner

zitec defcamp